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

    Neuronpedia

    INDEX
    Explanations

    sans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recognize
    -0.07
    .strokeStyle
    -0.07
    sockopt
    -0.06
    氏
    -0.06
     απ
    -0.06
     vivid
    -0.06
    oure
    -0.06
     Τι
    -0.06
    orrent
    -0.06
     HALF
    -0.06
    POSITIVE LOGITS
     utiliza
    0.06
    /',↵
    0.06
     قطر
    0.06
     Dar
    0.06
    uciones
    0.06
    占
    0.06
     sq
    0.06
     kvinner
    0.06
     brutal
    0.06
    _left
    0.06
    Act Density 0.036%

    No Known Activations