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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kol
    -0.07
     IsValid
    -0.07
     Nights
    -0.06
    __))
    -0.06
     matters
    -0.06
    ;%
    -0.06
     있던
    -0.06
     Weston
    -0.06
     offences
    -0.06
     Fucking
    -0.06
    POSITIVE LOGITS
     há
    0.08
     stra
    0.08
     A
    0.07
    -A
    0.07
     a
    0.07
    A
    0.07
    _a
    0.07
    /A
    0.06
    689
    0.06
    guard
    0.06
    Act Density 0.092%

    No Known Activations