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

    Neuronpedia

    INDEX
    Explanations

    apostrophe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leans
    -0.07
     dental
    -0.07
    Scalar
    -0.07
     팬
    -0.06
    ском
    -0.06
     behavioral
    -0.06
     Mang
    -0.06
     investigate
    -0.06
     qué
    -0.06
     leaned
    -0.06
    POSITIVE LOGITS
    ,filename
    0.07
     androidx
    0.06
    )'
    0.06
     &'
    0.06
    atility
    0.06
    Ар
    0.06
    ộc
    0.06
     自
    0.06
     tě
    0.06
    (Border
    0.06
    Act Density 0.008%

    No Known Activations