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

    Neuronpedia

    INDEX
    Explanations

    Technical/scientific contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WireFormat
    -0.85
    DockStyle
    -0.79
    yntaxException
    -0.77
     beginnetje
    -0.75
     Meksiku
    -0.69
    SourceChecksum
    -0.68
    utilisons
    -0.64
    StoryboardSegue
    -0.62
     مشين
    -0.62
     Relief
    -0.61
    POSITIVE LOGITS
     vientre
    0.40
     appena
    0.39
    googleapis
    0.38
    Clik
    0.37
    спо
    0.36
     keyPressed
    0.35
    nde
    0.35
     amat
    0.35
    Composable
    0.34
    de
    0.33
    Act Density 0.003%

    No Known Activations