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

    Neuronpedia

    INDEX
    Explanations

    utf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discusses
    -0.07
    (custom
    -0.07
    <J
    -0.06
    message
    -0.06
     criteria
    -0.06
    .rating
    -0.06
     활동
    -0.06
     ώρα
    -0.06
     usual
    -0.06
    -shopping
    -0.06
    POSITIVE LOGITS
    =utf
    0.09
     분
    0.07
    سام
    0.06
     pulumi
    0.06
    ่อต
    0.06
    RDD
    0.06
    _LP
    0.06
    icio
    0.06
    ulumi
    0.06
     ReturnType
    0.06
    Act Density 0.000%

    No Known Activations