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
    ten
    -0.07
    ARAM
    -0.06
    DI
    -0.06
    ouncer
    -0.06
     solitary
    -0.06
     adventurous
    -0.06
     volta
    -0.06
     گذ
    -0.06
    sat
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     mělo
    0.07
    ($"
    0.07
    <X
    0.07
     Exp
    0.07
     ~>
    0.07
     cracked
    0.06
     undermined
    0.06
    {↵↵↵
    0.06
     (%
    0.06
     контроль
    0.06
    Act Density 0.003%

    No Known Activations