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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ЕТ
    -0.07
     faut
    -0.07
     GetString
    -0.07
     учеб
    -0.06
    .CREATE
    -0.06
    .AddComponent
    -0.06
     statewide
    -0.06
     mieux
    -0.06
     선수
    -0.06
    Gay
    -0.06
    POSITIVE LOGITS
     Jacqueline
    0.07
    *m
    0.06
     troub
    0.06
    913
    0.06
    944
    0.06
    Broad
    0.06
    expand
    0.06
    叔
    0.06
     Rockets
    0.06
     �
    0.06
    Act Density 0.028%

    No Known Activations