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

    Neuronpedia

    INDEX
    Explanations

    features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
     grievances
    -0.06
    _backup
    -0.06
    truck
    -0.06
     동안
    -0.06
    .Password
    -0.06
     رب
    -0.06
     dvě
    -0.06
    أك
    -0.06
     createdBy
    -0.06
    POSITIVE LOGITS
    _slot
    0.07
    zos
    0.07
    abol
    0.06
    課
    0.06
     마법
    0.06
    ETIME
    0.06
    Чер
    0.06
    vably
    0.06
     microbes
    0.06
    amsung
    0.06
    Act Density 0.003%

    No Known Activations