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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anzi
    -0.06
    一致
    -0.06
     reversing
    -0.06
     experiencing
    -0.06
    arez
    -0.06
    先行
    -0.06
     ple
    -0.06
    不方便
    -0.06
     progressive
    -0.06
     aren
    -0.06
    POSITIVE LOGITS
    ceptar
    0.07
     getEmail
    0.07
    markup
    0.07
    rch
    0.07
     fiyat
    0.06
    与中国
    0.06
     dateTime
    0.06
    חיפוש
    0.06
    rides
    0.06
     minecraft
    0.06
    Act Density 0.005%

    No Known Activations