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

    Neuronpedia

    INDEX
    Explanations

    Descriptive details

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.73
     AttributeSet
    -0.72
    FunctionFlags
    -0.69
    ViewImports
    -0.66
    InstanceState
    -0.66
    Referències
    -0.65
    ंदीखरीदारी
    -0.65
    Referências
    -0.63
    Referensi
    -0.62
    Carriera
    -0.61
    POSITIVE LOGITS
     deep
    0.60
     a
    0.50
     Danish
    0.46
     Norwegian
    0.44
     strong
    0.43
     Sicilian
    0.43
     varme
    0.43
     warm
    0.42
     Libyan
    0.42
    NameInMap
    0.41
    Act Density 0.006%

    No Known Activations