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

    Neuronpedia

    INDEX
    Explanations

    Text HOME to 741741

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ৪০০
    0.48
    二百
    0.46
    鍱
    0.44
     فونیټ
    0.43
    ၣ
    0.42
     cvec
    0.42
    🜨
    0.42
    FindingsResponse
    0.41
     crebre
    0.40
    kfollowers
    0.39
    POSITIVE LOGITS
    7
    0.70
    0.67
    3
    0.59
    5
    0.59
    2
    0.57
    4
    0.57
    1
    0.57
    6
    0.54
    9
    0.44
    8
    0.44
    Act Density 0.043%

    No Known Activations