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

    Neuronpedia

    INDEX
    Explanations

    Menu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    moires
    -0.56
    lihood
    -0.44
    HANDLER
    -0.44
     montón
    -0.44
    cticut
    -0.42
    uoco
    -0.41
    ième
    -0.41
    loge
    -0.41
    äfte
    -0.41
    gages
    -0.41
    POSITIVE LOGITS
    matchCondition
    0.73
    الإنجليزية
    0.67
    IsContent
    0.66
    awtextra
    0.64
    UnsafeEnabled
    0.63
     <=",
    0.61
    StatusOK
    0.60
    piram
    0.60
     <>",
    0.60
     nonUne
    0.59
    Act Density 0.005%

    No Known Activations