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

    Neuronpedia

    INDEX
    Explanations

    send button click

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }=\
    2.92
     quede
    2.73
    ➢
    2.58
     pubblic
    2.57
    }>
    2.52
    িণী
    2.51
     том
    2.50
     biasa
    2.49
    ɳ
    2.49
    ⮚
    2.46
    POSITIVE LOGITS
    ience
    2.78
    ו
    2.73
    ু
    2.56
    off
    2.49
    ę
    2.41
    শীল
    2.32
    л
    2.31
    SDL
    2.26
    verein
    2.25
     ucfirst
    2.25
    Act Density 0.018%

    No Known Activations