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

    Neuronpedia

    INDEX
    Explanations

    programming steps or data presentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     not
    0.47
    0.45
     and
    0.45
     ventric
    0.45
     feitos
    0.44
     chewed
    0.43
     wis
    0.42
    みたい
    0.42
     biofuel
    0.42
     bo
    0.41
    POSITIVE LOGITS
    Ს
    0.45
    毽
    0.45
    大众
    0.45
    ıdır
    0.45
     কাঠামো
    0.44
    Გ
    0.43
    𒉈
    0.43
    Layer
    0.42
     Einwill
    0.42
    Რ
    0.42
    Act Density 0.000%

    No Known Activations