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

    Neuronpedia

    INDEX
    Explanations

    NSCoder encodeWithCoder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kapit
    -0.82
     IActionResult
    -0.81
     vaak
    -0.79
     Hydrogen
    -0.79
     госпо
    -0.77
    ökning
    -0.77
     jogadores
    -0.77
    (|
    -0.77
     filozof
    -0.76
     mie
    -0.73
    POSITIVE LOGITS
     Coding
    1.35
    Coding
    1.22
     coding
    1.13
    coding
    0.99
     Schlüssel
    0.96
    decoder
    0.88
     Decode
    0.87
     keyed
    0.85
     clés
    0.85
     decoder
    0.83
    Act Density 0.006%

    No Known Activations