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

    Neuronpedia

    INDEX
    Explanations

    deep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kyle
    -0.08
     barn
    -0.07
     Auschwitz
    -0.07
    _station
    -0.07
     learning
    -0.07
    灵
    -0.07
     ایشان
    -0.07
    IMP
    -0.07
     руках
    -0.07
     Ahmad
    -0.07
    POSITIVE LOGITS
    Include
    0.06
    不同的
    0.06
    _trampoline
    0.06
    ?,↵
    0.06
    ('--
    0.06
    _ip
    0.06
    $error
    0.05
    "',
    0.05
    ('-',
    0.05
     dul
    0.05
    Act Density 0.004%

    No Known Activations