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

    Neuronpedia

    INDEX
    Explanations

    both the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Internet
    0.56
     Executive
    0.51
     Karn
    0.51
     Sole
    0.48
     Silicon
    0.48
     Bacon
    0.48
     चालू
    0.47
     Back
    0.46
     Cel
    0.46
     Medical
    0.46
    POSITIVE LOGITS
     numerador
    0.69
    婪
    0.68
    ativamente
    0.65
     特
    0.64
    틋
    0.64
    ativement
    0.63
     TComponent
    0.63
    尴
    0.62
     logement
    0.60
     particulier
    0.59
    Act Density 0.000%

    No Known Activations