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

    Neuronpedia

    INDEX
    Explanations

    European things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    a
    -1.23
    e
    -1.20
    i
    -1.09
    o
    -0.98
    ی
    -0.85
    s
    -0.77
    y
    -0.75
    ا
    -0.73
    iyle
    -0.71
    eer
    -0.69
    POSITIVE LOGITS
     eccl
    0.49
    Disappear
    0.47
    iness
    0.47
    ism
    0.47
     BorderRadius
    0.47
     sauvage
    0.47
    ational
    0.47
    IONS
    0.47
    ledge
    0.46
    arian
    0.46
    Act Density 0.044%

    No Known Activations