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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fucking
    -0.08
    先
    -0.06
     ate
    -0.06
    徐
    -0.06
    НА
    -0.06
     halfway
    -0.06
     Кон
    -0.06
     sloppy
    -0.06
    -Cola
    -0.06
     readline
    -0.06
    POSITIVE LOGITS
    AGMENT
    0.07
    aporation
    0.07
    .npy
    0.06
     complicated
    0.06
    argin
    0.06
     comprehensive
    0.06
     salmon
    0.06
    -send
    0.06
     Ember
    0.06
    .conditions
    0.06
    Act Density 0.032%

    No Known Activations