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

    Neuronpedia

    INDEX
    Explanations

    Circuit miniaturization

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     interv
    -0.06
     differed
    -0.06
     cambio
    -0.06
     odds
    -0.06
     růz
    -0.06
     probe
    -0.06
    Mu
    -0.06
     skype
    -0.06
    temps
    -0.06
     dataframe
    -0.06
    POSITIVE LOGITS
     looph
    0.07
    pt
    0.07
    cancel
    0.06
    .Department
    0.06
     Sistem
    0.06
    addClass
    0.06
    annotation
    0.06
    CGPoint
    0.06
    captcha
    0.06
    Indeed
    0.06
    Act Density 0.066%

    No Known Activations