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

    Neuronpedia

    INDEX
    Explanations

    price range

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isko
    0.56
    iviato
    0.54
     doubling
    0.53
     horrified
    0.53
    addNew
    0.52
     fig
    0.51
     nis
    0.50
    龱
    0.50
     tä
    0.50
     adolesc
    0.49
    POSITIVE LOGITS
     MUCH
    0.70
     большое
    0.70
     MANY
    0.68
     аж
    0.66
     cocktails
    0.65
     IMMEDI
    0.62
     well
    0.61
     даже
    0.61
     muchos
    0.61
     Nhiều
    0.60
    Act Density 0.000%

    No Known Activations