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

    Neuronpedia

    INDEX
    Explanations

    example selectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    อดู
    0.43
    FFER
    0.41
    ignal
    0.35
    armonic
    0.35
     concor
    0.35
    ultats
    0.35
     同
    0.34
     bych
    0.34
     даль
    0.34
    odings
    0.34
    POSITIVE LOGITS
    Nowadays
    0.42
     nowadays
    0.39
     răng
    0.39
     Nowadays
    0.39
    سازی
    0.38
     wife
    0.38
     rudder
    0.38
     despite
    0.37
    asyarakat
    0.37
    啼
    0.37
    Act Density 0.000%

    No Known Activations