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

    Neuronpedia

    INDEX
    Explanations

    Web page performance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inequalities
    -0.08
    346
    -0.08
     hospitality
    -0.08
     always
    -0.08
                                                ↵
    -0.08
    机关
    -0.07
     crimes
    -0.07
     inequality
    -0.07
     Apt
    -0.07
    [length
    -0.07
    POSITIVE LOGITS
     شدن
    0.08
    TT
    0.08
     marx
    0.08
     firefox
    0.08
     rendimiento
    0.08
     blurry
    0.08
    Largest
    0.08
     നേ
    0.08
    Lowest
    0.08
     വൈക
    0.08
    Act Density 0.002%

    No Known Activations