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

    Neuronpedia

    INDEX
    Explanations

    Condition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MAY
    -0.06
     Bride
    -0.06
    ponsive
    -0.06
    -Д
    -0.06
    拔
    -0.06
    Few
    -0.06
    ㎡
    -0.06
     obr
    -0.06
    unprocessable
    -0.06
    .Null
    -0.06
    POSITIVE LOGITS
     �
    0.07
    ::↵
    0.06
    ย
    0.06
    の上
    0.06
     приг
    0.06
    otes
    0.06
     kappa
    0.06
    ルク
    0.06
     tai
    0.06
     animals
    0.06
    Act Density 0.000%

    No Known Activations