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

    Neuronpedia

    INDEX
    Explanations

    electrostatic

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sprite
    0.94
     byte
    0.87
     interaction
    0.83
     drug
    0.82
     potion
    0.79
     Portfolio
    0.78
     Bytes
    0.78
     epistle
    0.78
     bubble
    0.78
     drawn
    0.77
    POSITIVE LOGITS
    련
    0.78
    ců
    0.74
    我很
    0.72
     vjer
    0.72
    ëlle
    0.71
    цю
    0.71
    يلا
    0.71
    çi
    0.69
    ća
    0.68
    гава
    0.68
    Act Density 0.000%

    No Known Activations