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

    Neuronpedia

    INDEX
    Explanations

    ac

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     خارجية
    -0.66
     Савезне
    -0.65
    וויק
    -0.64
    currentColor
    -0.62
     AssemblyCompany
    -0.61
     Meksiku
    -0.60
    soever
    -0.59
    __':
    -0.58
    AndEndTag
    -0.57
     ligiloj
    -0.56
    POSITIVE LOGITS
     berta
    0.46
     M
    0.45
     createSlice
    0.45
    ГЛА
    0.44
     Caine
    0.44
     actionTypes
    0.43
    ubahan
    0.42
    mengen
    0.42
     Ba
    0.41
     Kane
    0.41
    Act Density 0.000%

    No Known Activations