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

    Neuronpedia

    INDEX
    Explanations

    version control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     только
    0.48
     मोठे
    0.46
     uniquement
    0.45
     deporte
    0.43
    ле
    0.43
     преподава
    0.43
    䬲
    0.43
     सीख
    0.42
     leer
    0.42
    टू
    0.42
    POSITIVE LOGITS
    acara
    0.47
    elio
    0.45
     SYM
    0.45
    vela
    0.45
    quera
    0.44
    ⑩
    0.44
    sunline
    0.44
     SUD
    0.43
    vidia
    0.43
    gorod
    0.42
    Act Density 0.000%

    No Known Activations