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

    Neuronpedia

    INDEX
    Explanations

    generally or overall

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ثل
    0.40
     inactivació
    0.36
    却是
    0.35
    অথ
    0.35
     tantôt
    0.34
     vaak
    0.33
     taas
    0.33
     moitié
    0.32
    osti
    0.32
     sofort
    0.31
    POSITIVE LOGITS
     overall
    2.98
     generally
    2.86
    overall
    2.66
     Overall
    2.58
    Overall
    2.58
     вообще
    2.53
    整体
    2.48
    generally
    2.45
    Generally
    2.42
     generell
    2.41
    Act Density 0.142%

    No Known Activations