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
     Often
    -0.07
    representation
    -0.07
    qui
    -0.06
     �
    -0.06
    Œ
    -0.06
     myster
    -0.06
     zwe
    -0.06
    guess
    -0.06
    strstr
    -0.06
    programs
    -0.06
    POSITIVE LOGITS
     اعتر
    0.07
     sack
    0.06
    _prom
    0.06
     Spoj
    0.06
    인지
    0.06
     enthusiast
    0.06
     integrate
    0.06
    _INSTANCE
    0.06
    _BLEND
    0.06
    igli
    0.06
    Act Density 0.112%

    No Known Activations