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

    Neuronpedia

    INDEX
    Explanations

    planets, names, programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apportionment
    0.47
     predicament
    0.46
     apportion
    0.45
     makeup
    0.45
     worsening
    0.45
     precession
    0.44
     sekarang
    0.43
     intermittent
    0.43
     maquillaje
    0.42
     cambiamenti
    0.42
    POSITIVE LOGITS
    LogProfile
    0.47
     Роб
    0.45
     Jean
    0.42
    lüğ
    0.42
    Jean
    0.42
     Francesco
    0.41
     Margaret
    0.40
    Roy
    0.40
     Roy
    0.39
     रॉय
    0.39
    Act Density 5.837%

    No Known Activations