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

    Neuronpedia

    INDEX
    Explanations

    guide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ...]↵↵
    -0.08
    >↵↵
    -0.07
    前三
    -0.07
    foreach
    -0.07
    晴
    -0.07
    among
    -0.07
    ...↵↵
    -0.07
     mø
    -0.07
    �
    -0.07
     ا
    -0.07
    POSITIVE LOGITS
     plagiar
    0.07
    镵
    0.07
     enlight
    0.06
    Channels
    0.06
     behaved
    0.06
    missive
    0.06
     Guitar
    0.06
    _apply
    0.06
     healed
    0.06
     widened
    0.06
    Act Density 0.009%

    No Known Activations