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

    Neuronpedia

    INDEX
    Explanations

    Lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     music
    -0.07
    千方百
    -0.07
    ✤
    -0.07
    _recall
    -0.06
     CATEGORY
    -0.06
    麟
    -0.06
    ♪↵↵
    -0.06
    Rights
    -0.06
     Pike
    -0.06
     MUSIC
    -0.06
    POSITIVE LOGITS
     Malaysia
    0.08
    ached
    0.08
    hör
    0.07
    .inf
    0.07
    ensem
    0.07
    ง
    0.07
    ahoma
    0.07
    𒀸
    0.07
     Contractors
    0.07
     subcontract
    0.07
    Act Density 0.010%

    No Known Activations