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

    Neuronpedia

    INDEX
    Explanations

    People's work history

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     respected
    -0.07
     machen
    -0.07
    ujących
    -0.07
     Grad
    -0.07
    _FREE
    -0.07
     EZ
    -0.07
    _GRE
    -0.06
     Vacuum
    -0.06
    疥
    -0.06
     prov
    -0.06
    POSITIVE LOGITS
    .isDebugEnabled
    0.08
    /dc
    0.07
     주장
    0.06
     urlString
    0.06
    とっても
    0.06
    -"
    0.06
     opin
    0.06
     moto
    0.06
     dost
    0.06
    伤害
    0.06
    Act Density 0.095%

    No Known Activations