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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    otyp
    -0.06
     bras
    -0.06
     кост
    -0.06
     mirror
    -0.06
     гот
    -0.06
    agina
    -0.06
    Laughs
    -0.06
    센터
    -0.06
    bing
    -0.06
    .Clear
    -0.06
    POSITIVE LOGITS
    ività
    0.07
    Ver
    0.07
    isme
    0.07
    //--------------------------------------------------------------------------------
    0.06
    智能
    0.06
     reversible
    0.06
    Reaction
    0.06
    ्ञ
    0.06
    婚
    0.06
     angle
    0.06
    Act Density 0.000%

    No Known Activations