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

    Neuronpedia

    INDEX
    Explanations

    sure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cheid
    -0.08
    acet
    -0.07
    _fd
    -0.07
     cyan
    -0.07
    ạp
    -0.07
    _Node
    -0.07
     subst
    -0.07
    olith
    -0.07
     ith
    -0.07
     Coastal
    -0.06
    POSITIVE LOGITS
     sure
    0.10
    Sure
    0.09
     Sure
    0.09
    sure
    0.09
    ensure
    0.08
     unsure
    0.08
     surely
    0.07
    _VER
    0.07
     surprises
    0.06
     score
    0.06
    Act Density 0.021%

    No Known Activations