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

    Neuronpedia

    INDEX
    Explanations

    ) ->

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Come
    0.71
    othor
    0.66
     uko
    0.64
    come
    0.63
    äksi
    0.63
     পরিচাল
    0.63
    いただき
    0.63
    stabil
    0.63
    Stabil
    0.62
     CSO
    0.61
    POSITIVE LOGITS
     ->
    2.02
     →
    1.69
    ->
    1.43
     -->
    1.28
    →
    1.21
    _->
    1.16
    ->"
    1.15
    ->$
    1.11
    ")->
    1.10
    ->_
    1.07
    Act Density 0.003%

    No Known Activations