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

    Neuronpedia

    INDEX
    Explanations

    date and time formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PED
    0.42
     പാര്‍
    0.41
     forests
    0.40
     امن
    0.38
     interven
    0.38
     decorated
    0.37
     бое
    0.37
    &+
    0.36
     woods
    0.36
    SDD
    0.36
    POSITIVE LOGITS
    சே
    0.41
     H
    0.40
     Prom
    0.40
     timestamp
    0.39
    ろし
    0.39
     d
    0.39
     sows
    0.38
    ｌ
    0.38
    jst
    0.38
     Timestamp
    0.38
    Act Density 0.003%

    No Known Activations