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

    Neuronpedia

    INDEX
    Explanations

    topics and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    striatis
    0.46
    piej
    0.43
     pptn
    0.43
    cluso
    0.42
     этими
    0.42
     हिस्से
    0.41
    vaegir
    0.40
     suburbs
    0.40
    ffekt
    0.40
     ดังนั้น
    0.40
    POSITIVE LOGITS
    The
    0.40
     is
    0.39
    <0xEF>
    0.39
     The
    0.38
     was
    0.37
    \
    0.36
     |
    0.36
     لا
    0.36
     la
    0.35
    A
    0.35
    Act Density 0.455%

    No Known Activations