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

    Neuronpedia

    INDEX
    Explanations

    iveness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AVE
    -0.07
     passport
    -0.07
    acs
    -0.07
    rase
    -0.07
    raž
    -0.07
    .pull
    -0.06
    �
    -0.06
    school
    -0.06
    áh
    -0.06
    Range
    -0.06
    POSITIVE LOGITS
    μαν
    0.06
    columnName
    0.06
     digging
    0.06
     Equipment
    0.06
    ()];↵
    0.06
     *)&
    0.06
    ］
    0.05
    Nit
    0.05
    ToSend
    0.05
    .writeInt
    0.05
    Act Density 0.004%

    No Known Activations