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

    Neuronpedia

    INDEX
    Explanations

    connecting clauses and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ুতের
    0.44
     surgeries
    0.38
    лизм
    0.36
     ஏழு
    0.36
    سل
    0.36
    doesn
    0.36
     fó
    0.36
    +.
    0.35
     CRF
    0.35
    )))
    0.34
    POSITIVE LOGITS
     Singer
    0.40
    akka
    0.40
     ""`
    0.38
    GISLATIVE
    0.38
    Singer
    0.38
     열심히
    0.38
     zve
    0.36
     रोप
    0.36
    霭
    0.36
    arankan
    0.36
    Act Density 0.009%

    No Known Activations