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

    Neuronpedia

    INDEX
    Explanations

    search online or on websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desarrollar
    0.40
    חש
    0.38
     часть
    0.38
     opere
    0.38
    PartOf
    0.38
     Garbage
    0.38
     Makefile
    0.37
    OPENJDK
    0.37
     জাতিসংঘের
    0.37
    ？](
    0.36
    POSITIVE LOGITS
     or
    0.52
    or
    0.42
     eller
    0.41
     filters
    0.40
    ar
    0.40
    um
    0.40
    ular
    0.40
    หรือ
    0.39
     hoặc
    0.39
    ons
    0.39
    Act Density 0.024%

    No Known Activations