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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     valueForKey
    -0.06
    _encrypt
    -0.06
    forest
    -0.06
    -h
    -0.06
     trophy
    -0.06
     �
    -0.06
    Rocket
    -0.05
    جات
    -0.05
     требует
    -0.05
    hit
    -0.05
    POSITIVE LOGITS
    {})↵
    0.07
    acons
    0.07
    stell
    0.07
    Virtual
    0.07
    Marco
    0.07
     Amsterdam
    0.07
     Dyn
    0.06
    项目
    0.06
     tarihinde
    0.06
    cem
    0.06
    Act Density 0.004%

    No Known Activations