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

    Neuronpedia

    INDEX
    Explanations

    idea

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Koch
    -0.07
    ambient
    -0.06
    بال
    -0.06
    lfw
    -0.06
    SpecWarn
    -0.06
    etak
    -0.06
    authorize
    -0.06
    expectException
    -0.06
    _routes
    -0.06
    emphasis
    -0.06
    POSITIVE LOGITS
    xEC
    0.07
     Ideas
    0.07
     idea
    0.07
     Gabri
    0.06
     مشکل
    0.06
    VERS
    0.06
     JR
    0.06
     時
    0.06
    .facebook
    0.06
    범
    0.06
    Act Density 0.038%

    No Known Activations