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

    Neuronpedia

    INDEX
    Explanations

    code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ived
    0.42
     total
    0.40
    one
    0.39
     particular
    0.38
     pins
    0.38
    iden
    0.37
     impervious
    0.36
     Asian
    0.36
     pinpoint
    0.36
    ware
    0.36
    POSITIVE LOGITS
    <unused474>
    0.54
     اولم
    0.51
     Beweg
    0.48
     montré
    0.48
     expectativa
    0.47
     साँप
    0.47
     панели
    0.47
    룀
    0.47
     triángulos
    0.46
     девя
    0.46
    Act Density 0.000%

    No Known Activations