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

    Neuronpedia

    INDEX
    Explanations

    opening terminal or command prompt to visit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dériv
    0.44
     laissez
    0.42
     inherently
    0.39
     inherent
    0.37
     effect
    0.36
    ffect
    0.36
     rebut
    0.36
     দারিদ্র
    0.36
     shocking
    0.35
     plausible
    0.35
    POSITIVE LOGITS
     visitar
    0.56
     visiting
    0.54
     bezoek
    0.52
     visit
    0.49
     visitare
    0.48
     visita
    0.48
     visiter
    0.47
     ziyaret
    0.47
    visit
    0.45
     방문
    0.45
    Act Density 0.043%

    No Known Activations