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

    Neuronpedia

    INDEX
    Explanations

    brands, functions, range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ப்ளாக்
    0.49
     aktywn
    0.43
    inizi
    0.42
     Knoten
    0.40
     inizi
    0.40
    osti
    0.40
    rieren
    0.40
     निव
    0.40
     aplik
    0.39
    ダンス
    0.39
    POSITIVE LOGITS
    ин
    0.40
     shelled
    0.38
     quest
    0.38
     FSA
    0.37
     Ender
    0.36
     SCD
    0.36
    FileSystem
    0.35
    ото
    0.34
     CDP
    0.34
    <code>
    0.34
    Act Density 0.000%

    No Known Activations