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

    Neuronpedia

    INDEX
    Explanations

    job requirements related to friendliness and approachability

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

    Category lists and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    -0.38
     "
    -0.37
     weiterer
    -0.34
    “
    -0.32
    前回の
    -0.30
    Inflater
    -0.30
     circonst
    -0.29
    ワイイ
    -0.29
    としての
    -0.29
     “
    -0.29
    POSITIVE LOGITS
    Vidite
    0.79
    Portail
    0.70
    yarnpkg
    0.68
    kheim
    0.68
     Portail
    0.68
    writeFieldEnd
    0.68
     Italijani
    0.65
    ➯
    0.65
    ⟬
    0.65
     springfox
    0.65
    Act Density 0.007%

    No Known Activations