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

    Neuronpedia

    INDEX
    Explanations

    PS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hansen
    -0.07
     rezerv
    -0.06
     randomNumber
    -0.06
    -parser
    -0.06
    icked
    -0.06
     scanner
    -0.06
     Levine
    -0.06
     knight
    -0.06
     odpad
    -0.06
     вед
    -0.06
    POSITIVE LOGITS
    memory
    0.07
    OSP
    0.06
    -loving
    0.06
    бом
    0.06
    ुआत
    0.06
     PARA
    0.06
     انواع
    0.06
    ativní
    0.06
    ær
    0.06
     creative
    0.06
    Act Density 0.052%

    No Known Activations