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

    Neuronpedia

    INDEX
    Explanations

    JSON keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.48
    inoceros
    0.45
     convoluted
    0.44
     Squirrel
    0.43
     Le
    0.42
    散热
    0.41
     Soy
    0.40
     sullen
    0.40
     valign
    0.40
     Barley
    0.39
    POSITIVE LOGITS
    ها
    0.56
    <unused287>
    0.54
    <unused1861>
    0.54
    <unused597>
    0.53
    <unused681>
    0.52
    <unused99>
    0.52
    <unused509>
    0.52
    <unused312>
    0.51
    <unused1921>
    0.51
    ANG
    0.51
    Act Density 0.011%

    No Known Activations