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

    Neuronpedia

    INDEX
    Explanations

    links and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     four
    0.39
     f
    0.38
     Incoming
    0.37
     fascinating
    0.37
     eight
    0.36
     promedio
    0.36
     exactamente
    0.35
     پانچ
    0.35
     incoming
    0.35
     Exc
    0.35
    POSITIVE LOGITS
    hôpital
    0.38
    menuCategory
    0.38
     度
    0.38
     হৈ
    0.38
    മീ
    0.38
    ကာ
    0.38
    ఙ
    0.38
    ♥️
    0.37
    buttonBar
    0.37
    protein
    0.37
    Act Density 0.000%

    No Known Activations