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

    Neuronpedia

    INDEX
    Explanations

    .io

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     JNIEnv
    -0.07
     Arguments
    -0.07
     URLWithString
    -0.07
    lower
    -0.07
    avored
    -0.07
    clud
    -0.06
     الطريق
    -0.06
     קצר
    -0.06
     diseñ
    -0.06
    冁
    -0.06
    POSITIVE LOGITS
    وض
    0.08
     residences
    0.08
    ZW
    0.07
     hver
    0.07
     sempre
    0.07
    SG
    0.07
     XF
    0.07
     Hyp
    0.07
     Nations
    0.07
    斐
    0.07
    Act Density 0.001%

    No Known Activations