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

    Neuronpedia

    INDEX
    Explanations

    expressions of confidence

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     McK
    -0.07
    ck
    -0.07
     gre
    -0.06
    jab
    -0.06
     criteria
    -0.06
    lap
    -0.06
     Matth
    -0.06
    ada
    -0.06
     totiž
    -0.06
     cab
    -0.06
    POSITIVE LOGITS
    iaux
    0.08
     it
    0.07
    eci
    0.07
    hower
    0.07
    osy
    0.06
    Result
    0.06
    LOAT
    0.06
    agal
    0.06
     tavs
    0.06
    answer
    0.06
    Act Density 0.023%

    No Known Activations