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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LVL
    -0.07
     засід
    -0.07
    EST
    -0.06
     حذف
    -0.06
    .EntityManager
    -0.06
    ariate
    -0.06
    'app
    -0.06
     اج
    -0.06
     túi
    -0.06
    _jobs
    -0.05
    POSITIVE LOGITS
    听到
    0.07
    รร
    0.07
    _special
    0.06
    Modifiers
    0.06
     Shr
    0.06
    _column
    0.06
    ینگ
    0.06
    <V
    0.06
     Gonzalez
    0.06
    Vintage
    0.06
    Act Density 0.018%

    No Known Activations