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

    Neuronpedia

    INDEX
    Explanations

    generating php code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Computer
    0.85
    Impl
    0.83
    Ware
    0.82
    projection
    0.80
    Numero
    0.78
    Agency
    0.75
    ((
    0.74
    computer
    0.73
    :/
    0.73
    propagation
    0.72
    POSITIVE LOGITS
     Unterkunft
    0.89
     lawsuit
    0.74
    を提供する
    0.74
     sonic
    0.72
    ᵏ
    0.71
     lyrics
    0.71
     superb
    0.70
     sooner
    0.69
     logLevel
    0.69
     arrest
    0.69
    Act Density 0.001%

    No Known Activations