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

    Neuronpedia

    INDEX
    Explanations

    Ctrl + Shift + Esc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stad
    0.47
    ధం
    0.47
    Freq
    0.46
    allerg
    0.45
     Eğer
    0.44
    sa
    0.44
    ﻯ
    0.43
    igated
    0.43
    Xa
    0.43
    smittel
    0.43
    POSITIVE LOGITS
    지
    0.48
     garages
    0.46
     agriculture
    0.45
    க்
    0.43
     refineries
    0.41
     архитек
    0.41
     publicly
    0.41
    ុស
    0.40
    aun
    0.40
     pública
    0.40
    Act Density 0.003%

    No Known Activations