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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing importance, mutual understanding, and cultural insights

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

    vampires and active

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dAtA
    -0.28
    才
    -0.27
     areia
    -0.26
     estan
    -0.25
    assertRaises
    -0.25
     sodass
    -0.25
    ResId
    -0.24
     אחר
    -0.24
    BeginContext
    -0.24
    taines
    -0.24
    POSITIVE LOGITS
    ftagPool
    0.81
    ⟬
    0.69
    0.66
     CreateTagHelper
    0.63
    SequentialGroup
    0.61
    AddTagHelper
    0.59
    -------
    0.59
     flexible
    0.59
    новништво
    0.57
     useAppContext
    0.56
    Act Density 0.026%

    No Known Activations