Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions related to the limitations of language in conveying profound experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Inability to describe or articulate

    np_acts-logits-general · gemini-2.0-flash

    difficulty describing or summing up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.55
    ettbewer
    -0.47
    proof
    -0.47
    consult
    -0.46
    delwed
    -0.45
    новниш
    -0.45
    Spoljašnje
    -0.45
    Proof
    -0.44
     Consult
    -0.44
    flexible
    -0.43
    POSITIVE LOGITS
     وصف
    0.43
     describir
    0.40
    XmlEnum
    0.40
     décrire
    0.40
     indescribable
    0.39
     describes
    0.38
     words
    0.38
    getWriter
    0.37
     anlat
    0.35
     simulation
    0.34
    Act Density 0.182%

    No Known Activations