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

    Neuronpedia

    INDEX
    Explanations

    geometric projections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anya
    0.42
     Phrases
    0.41
    砵
    0.41
    đena
    0.40
     ++)
    0.39
     باتیں
    0.39
     الحق
    0.39
     растения
    0.38
     있지만
    0.38
    桩
    0.38
    POSITIVE LOGITS
     onto
    0.70
     into
    0.51
     projection
    0.50
     projecting
    0.49
     project
    0.46
     projected
    0.46
     on
    0.46
    Projection
    0.46
     Project
    0.45
     Projection
    0.45
    Act Density 0.005%

    No Known Activations