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

    Neuronpedia

    INDEX
    Explanations

    Code and internet language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     propOrder
    -0.92
    OGND
    -0.83
    EndInit
    -0.77
    StoryboardSegue
    -0.74
    NewGuid
    -0.69
     createSlice
    -0.65
    WaitGroup
    -0.65
    Personendaten
    -0.65
     doigts
    -0.64
    iddhar
    -0.63
    POSITIVE LOGITS
     nakalista
    0.45
     AU
    0.43
     aus
    0.43
     lasting
    0.41
    يلات
    0.41
     out
    0.41
    ifrance
    0.40
     made
    0.39
    anius
    0.39
    fø
    0.39
    Act Density 0.001%

    No Known Activations