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

    Neuronpedia

    INDEX
    Explanations

    multiple items combined

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ए
    0.57
    🇼
    0.55
    STATE
    0.54
    ália
    0.54
    June
    0.52
    October
    0.52
    GÁ
    0.52
    उ
    0.52
    🇶
    0.52
    EXTERNAL
    0.51
    POSITIVE LOGITS
    fen
    0.53
     computations
    0.47
    led
    0.45
     Bell
    0.44
     Di
    0.44
    zen
    0.43
     ثلاث
    0.43
    fork
    0.43
     Fletcher
    0.43
    iana
    0.42
    Act Density 0.000%

    No Known Activations