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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UCKET
    -0.06
     '@
    -0.06
    _particle
    -0.06
     kp
    -0.06
    hv
    -0.06
     shark
    -0.06
    мож
    -0.06
     高
    -0.06
     trails
    -0.05
     transc
    -0.05
    POSITIVE LOGITS
     cup
    0.07
    indow
    0.07
     EB
    0.07
     Tub
    0.06
    _OFF
    0.06
    !.↵↵
    0.06
    .Transparent
    0.06
     TB
    0.06
     nev
    0.06
     Trends
    0.06
    Act Density 0.011%

    No Known Activations