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

    Neuronpedia

    INDEX
    Explanations

    sentiment score

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     multiplicities
    0.44
     multiplicity
    0.40
     фаразы
    0.39
    해보
    0.39
     gathering
    0.38
    㳯
    0.38
     ставак
    0.38
     wcex
    0.38
     LocalDate
    0.38
     subsum
    0.38
    POSITIVE LOGITS
     salvar
    0.43
     値
    0.43
    chave
    0.41
     Resmi
    0.41
     farewell
    0.41
     tidur
    0.41
     झेल
    0.38
     ’’
    0.36
    pray
    0.36
    fowl
    0.36
    Act Density 0.020%

    No Known Activations