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

    Neuronpedia

    INDEX
    Explanations

    care about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ્ન
    0.73
     інших
    0.69
    ন
    0.65
     ಇತರ
    0.64
     Mexiko
    0.63
     書い
    0.63
     Unsere
    0.62
    OGR
    0.60
    OCR
    0.59
     Urdu
    0.59
    POSITIVE LOGITS
     and
    0.85
     is
    0.81
    ↵
    0.78
     was
    0.73
     .
    0.63
    ness
    0.60
    issime
    0.58
    ية
    0.55
     banget
    0.54
    ся
    0.53
    Act Density 0.148%

    No Known Activations