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

    Neuronpedia

    INDEX
    Explanations

    the word "tears" and related emotional expressions

    oai_token-act-pair · gemini-2.0-flash

    tears

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.89
     aDecoder
    -0.80
    MigrationBuilder
    -0.77
    writeFieldEnd
    -0.73
    LookAnd
    -0.71
    Obrázky
    -0.66
     Drittan
    -0.64
     ويكيميديا
    -0.64
    protoimpl
    -0.63
    Rohy
    -0.61
    POSITIVE LOGITS
    etheless
    0.84
    fuls
    0.67
    ressee
    0.66
    Datuak
    0.62
    jectures
    0.61
    llano
    0.60
    numerusform
    0.60
    脚注の使い方
    0.59
    zwischen
    0.58
    }');
    0.57
    Act Density 2.041%

    No Known Activations