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

    Neuronpedia

    INDEX
    Explanations

    out or outwards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dear
    0.68
    AGES
    0.66
    Gut
    0.62
     kegiatan
    0.61
    olok
    0.61
    Owned
    0.61
     Dear
    0.61
     activities
    0.60
     requesting
    0.60
     transitioned
    0.60
    POSITIVE LOGITS
     Uit
    0.87
    戝
    0.79
     pys
    0.78
     બહાર
    0.78
     Ausgabe
    0.77
    cantidad
    0.76
     outwards
    0.76
    ovirus
    0.75
    eluarkan
    0.74
     fuori
    0.74
    Act Density 0.000%

    No Known Activations