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

    Neuronpedia

    INDEX
    Explanations

    say "no"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ROW
    -0.08
    Comb
    -0.07
     �
    -0.07
     Fold
    -0.07
    RuleContext
    -0.06
    mo
    -0.06
     Quân
    -0.06
    provided
    -0.06
     restaur
    -0.06
    stå
    -0.06
    POSITIVE LOGITS
    %A
    0.07
    roller
    0.06
    čního
    0.06
    PointerException
    0.06
     worldly
    0.06
     Colts
    0.06
    (round
    0.06
     ober
    0.06
     Harper
    0.06
    аров
    0.06
    Act Density 0.007%

    No Known Activations