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

    Neuronpedia

    INDEX
    Explanations

    reviews and descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ability
    -0.06
     رو
    -0.06
    ============
    -0.06
    лич
    -0.06
    -negative
    -0.06
    CFG
    -0.06
    ौज
    -0.06
     mocked
    -0.06
     ورود
    -0.06
    علی
    -0.06
    POSITIVE LOGITS
    .Align
    0.07
     чемпион
    0.07
     IEEE
    0.06
     southwestern
    0.06
     haar
    0.06
    :create
    0.06
    Cit
    0.06
    _face
    0.06
     hairstyle
    0.06
    ικό
    0.06
    Act Density 0.338%

    No Known Activations