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

    Neuronpedia

    INDEX
    Explanations

    animal experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    ِي
    -0.07
    uum
    -0.06
    _OBJ
    -0.06
    ण
    -0.06
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    -0.06
    وس
    -0.06
    EMBER
    -0.06
     evangel
    -0.06
    ूँ
    -0.06
    POSITIVE LOGITS
    |=↵
    0.06
    teachers
    0.06
    compression
    0.06
     commission
    0.06
     Poll
    0.06
     "'"
    0.06
    -coded
    0.06
     commissions
    0.06
    059
    0.06
    ByName
    0.06
    Act Density 0.040%

    No Known Activations