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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Spider
    -0.07
    chsel
    -0.07
    却
    -0.07
    wald
    -0.06
    ながら
    -0.06
     začala
    -0.06
     开
    -0.06
     gấp
    -0.06
     scared
    -0.06
     سبب
    -0.06
    POSITIVE LOGITS
    مول
    0.07
    .firebaseio
    0.07
     subsequent
    0.06
     Wonder
    0.06
     chic
    0.06
     atrav
    0.06
    gregated
    0.06
    LOOK
    0.06
     vis
    0.06
    ereum
    0.06
    Act Density 0.000%

    No Known Activations