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

    Neuronpedia

    INDEX
    Explanations

    re

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “This
    -0.08
    imeline
    -0.07
    _timeline
    -0.07
    .pix
    -0.07
    “In
    -0.07
    める
    -0.07
    "This
    -0.06
    ategorias
    -0.06
     Broad
    -0.06
     Opportunity
    -0.06
    POSITIVE LOGITS
     ба
    0.07
     remar
    0.07
     Dre
    0.07
    omanip
    0.07
     Kore
    0.07
    �
    0.06
     Male
    0.06
     antibiot
    0.06
    bane
    0.06
    َح
    0.06
    Act Density 0.002%

    No Known Activations