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

    Neuronpedia

    INDEX
    Explanations

    mer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     giấc
    -0.08
     bú
    -0.08
    browse
    -0.07
    import
    -0.07
     userid
    -0.07
     spends
    -0.07
     glyc
    -0.07
    سوء
    -0.07
     סי
    -0.07
    吩咐
    -0.07
    POSITIVE LOGITS
     Cornell
    0.07
    ORK
    0.07
    ////////////
    0.07
    树林
    0.07
    𬪩
    0.07
     Modelo
    0.06
    Up
    0.06
    没人
    0.06
     obsession
    0.06
     סביב
    0.06
    Act Density 0.001%

    No Known Activations