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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Frameworks
    -0.07
    人口
    -0.06
    Logging
    -0.06
     Animalia
    -0.06
    Expires
    -0.06
    анов
    -0.06
     herb
    -0.06
    .LabelControl
    -0.06
     الولايات
    -0.06
     Cyber
    -0.06
    POSITIVE LOGITS
    astic
    0.07
     unpl
    0.07
     �
    0.06
     ин
    0.06
    _pl
    0.06
    ightly
    0.06
     nội
    0.06
     высокой
    0.06
    emonic
    0.06
     Att
    0.06
    Act Density 0.001%

    No Known Activations