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

    Neuronpedia

    INDEX
    Explanations

    should

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.68
     autorytatywna
    -0.66
    likon
    -0.57
     دیکھیے
    -0.57
    TargetException
    -0.56
     Préférences
    -0.55
    bootstrapcdn
    -0.55
    ыгана
    -0.54
    قایناقلار
    -0.53
     Kombat
    -0.52
    POSITIVE LOGITS
    n
    0.59
    a
    0.57
    DispatchToProps
    0.52
    s
    0.49
    deckte
    0.49
    ntä
    0.48
    v
    0.48
    ⁿ
    0.48
    tors
    0.47
     jug
    0.47
    Act Density 0.026%

    No Known Activations