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

    Neuronpedia

    INDEX
    Explanations

    research limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mingling
    0.33
     concealing
    0.33
    Celeron
    0.32
     rollerskates
    0.32
     godziny
    0.32
     تغيير
    0.31
    Merging
    0.31
     keySchedule
    0.31
     convolutions
    0.31
     scrollBody
    0.31
    POSITIVE LOGITS
    2
    0.43
    9
    0.41
    8
    0.38
     सन
    0.37
    1
    0.36
    7
    0.35
    in
    0.35
    ag
    0.34
    or
    0.34
    ib
    0.33
    Act Density 0.011%

    No Known Activations