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

    Neuronpedia

    INDEX
    Explanations

    steep

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Н
    0.40
     जबकि
    0.39
     WHILE
    0.37
     Swallow
    0.36
    perature
    0.35
     Possible
    0.35
     SCR
    0.35
     decidir
    0.34
    ACITY
    0.34
    ுகிறார்கள்
    0.33
    POSITIVE LOGITS
    edTest
    0.44
     پیک
    0.40
     Steep
    0.40
     dream
    0.39
    eggi
    0.39
    issimo
    0.38
     steep
    0.38
    艳
    0.38
    ifest
    0.38
     rêve
    0.38
    Act Density 0.000%

    No Known Activations