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

    Neuronpedia

    INDEX
    Explanations

    implementation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    translator
    -0.07
    👓
    -0.07
    .intValue
    -0.07
     Coupe
    -0.07
    Corporate
    -0.07
    <Boolean
    -0.07
    澌
    -0.07
     decentral
    -0.07
    觖
    -0.07
     elabor
    -0.07
    POSITIVE LOGITS
    放映
    0.09
    中信
    0.08
    퉜
    0.07
    objet
    0.07
    :"
    0.07
    arc
    0.07
     MB
    0.07
    払
    0.07
     ORD
    0.07
     borders
    0.07
    Act Density 0.007%

    No Known Activations