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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    вет
    -0.07
    zilla
    -0.06
    PathComponent
    -0.06
     zaman
    -0.06
    коном
    -0.06
    PRESSION
    -0.06
     жар
    -0.06
    quake
    -0.06
    (pk
    -0.06
    nič
    -0.06
    POSITIVE LOGITS
    /device
    0.07
     disappointed
    0.07
    ерт
    0.06
     contraception
    0.06
    Given
    0.06
     experimented
    0.06
    =input
    0.06
    :last
    0.06
     hairstyle
    0.06
     اولین
    0.06
    Act Density 0.000%

    No Known Activations