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

    Neuronpedia

    INDEX
    Explanations

    Async operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.66
    d
    0.63
     dich
    0.63
     Hilfe
    0.61
    us
    0.60
    ون
    0.59
     Vag
    0.59
     victorias
    0.59
    er
    0.58
    ようになりました
    0.58
    POSITIVE LOGITS
    侎
    0.82
    берите
    0.72
    și
    0.71
     eruptions
    0.69
    した
    0.69
    setHeader
    0.68
     surfacing
    0.67
     Asociación
    0.66
    exitTool
    0.66
    yaxis
    0.65
    Act Density 0.002%

    No Known Activations