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

    Neuronpedia

    INDEX
    Explanations

    relies on function or name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ighth
    0.58
    school
    0.50
    s
    0.49
    item
    0.49
     geme
    0.49
     pab
    0.49
     مح
    0.48
    h
    0.48
    length
    0.48
     leider
    0.48
    POSITIVE LOGITS
    쐞
    0.49
    얕
    0.49
     ITU
    0.45
    펀
    0.45
    PRIM
    0.45
    PLOAD
    0.45
    olique
    0.44
     combustibles
    0.44
    поте
    0.44
     dago
    0.44
    Act Density 0.000%

    No Known Activations