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

    Neuronpedia

    INDEX
    Explanations

    tolerance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ymax
    -0.07
     impulse
    -0.07
     inherits
    -0.07
     rewards
    -0.06
     nursery
    -0.06
    prev
    -0.06
    ，她
    -0.06
    Connect
    -0.06
     rects
    -0.06
     thrill
    -0.06
    POSITIVE LOGITS
    BAL
    0.06
     LAW
    0.06
    -pol
    0.06
    Traditional
    0.06
     Lomb
    0.06
    .tc
    0.06
    kont
    0.06
    "."
    0.06
    tok
    0.06
    ahr
    0.06
    Act Density 0.003%

    No Known Activations