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

    Neuronpedia

    INDEX
    Explanations

    old

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (rand
    -0.07
    рахов
    -0.07
     VERSION
    -0.07
    )});↵
    -0.07
     march
    -0.07
    .heading
    -0.06
    -desktop
    -0.06
    rito
    -0.06
     pedal
    -0.06
    ("{}
    -0.06
    POSITIVE LOGITS
    eld
    0.10
     Feld
    0.08
    elder
    0.07
    ild
    0.07
    ILD
    0.07
     فول
    0.07
    dı
    0.07
     Weld
    0.07
    ield
    0.07
     Yield
    0.07
    Act Density 0.032%

    No Known Activations