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

    Neuronpedia

    INDEX
    Explanations

    school sports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tones
    -0.07
     يون
    -0.07
    🇿
    -0.07
    lovak
    -0.06
    ،
    -0.06
    _LITERAL
    -0.06
     boarded
    -0.06
    _fire
    -0.06
     haz
    -0.06
    톤
    -0.06
    POSITIVE LOGITS
    نع
    0.07
    Prop
    0.07
    ASURE
    0.07
    ifact
    0.07
    ausal
    0.07
    小女孩
    0.07
    וצאה
    0.07
     מעט
    0.07
    少なく
    0.07
    缩短
    0.07
    Act Density 0.096%

    No Known Activations