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

    Neuronpedia

    INDEX
    Explanations

    .Threading

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ert
    -0.07
     استفاده
    -0.07
     زاد
    -0.06
     lunch
    -0.06
     　　
    -0.06
    /sdk
    -0.06
     cloak
    -0.06
    _topology
    -0.06
    ULK
    -0.06
     see
    -0.06
    POSITIVE LOGITS
     Ис
    0.06
     لها
    0.06
    ERICAN
    0.06
    _contrib
    0.06
    »:
    0.06
    abr
    0.06
     Invitation
    0.06
     German
    0.06
    кування
    0.06
    alama
    0.06
    Act Density 0.003%

    No Known Activations