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

    Neuronpedia

    INDEX
    Explanations

    Separators/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /
    -0.82
    -
    -0.80
    –
    -0.78
    "
    -0.65
    (
    -0.60
     виправивши
    -0.60
    Datuak
    -0.59
    −
    -0.58
    -$
    -0.57
     + 
    -0.57
    POSITIVE LOGITS
     vPvB
    0.74
    
    0.63
     suspendu
    0.55
     CreateTagHelper
    0.55
    ViewImports
    0.54
     lenker
    0.52
    -------
    0.52
    rewsbury
    0.51
     ujednoznacz
    0.51
     DialogInterface
    0.50
    Act Density 0.064%

    No Known Activations