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

    Neuronpedia

    INDEX
    Explanations

    Reduced operational

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilmiş
    0.42
    閥
    0.40
     எதிர்க
    0.40
    水位
    0.38
    mano
    0.38
    oline
    0.38
     orientated
    0.37
    flav
    0.37
    にっいて
    0.37
    侷
    0.37
    POSITIVE LOGITS
     prodigious
    0.42
     impulsive
    0.40
     الإمارات
    0.40
     exceedingly
    0.39
     mod
    0.39
     високо
    0.39
     超
    0.38
    وبي
    0.38
    たっぷり
    0.37
     complex
    0.37
    Act Density 0.000%

    No Known Activations