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

    Neuronpedia

    INDEX
    Explanations

    Punctuation/Symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /D
    -0.06
    ,d
    -0.06
    ,double
    -0.06
     обязан
    -0.06
    .LocalDateTime
    -0.06
     해
    -0.06
    .cl
    -0.06
     Ка
    -0.06
     cał
    -0.06
     Voy
    -0.06
    POSITIVE LOGITS
    hip
    0.07
    ↵↵↵↵↵↵↵↵↵↵
    0.06
    ालन
    0.06
    งเป
    0.06
    ilim
    0.06
    terror
    0.06
     Presence
    0.06
    'elle
    0.06
     Larger
    0.06
     extrem
    0.06
    Act Density 0.093%

    No Known Activations