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

    Neuronpedia

    INDEX
    Explanations

    simple visualizations, Circle, past

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.46
     EU
    0.46
    },
    0.44
     pictures
    0.44
     chiq
    0.44
     together
    0.43
     RO
    0.43
     assist
    0.43
     Leg
    0.42
     assistant
    0.42
    POSITIVE LOGITS
    ర్‌లో
    0.51
    жі
    0.50
    اقة
    0.49
     liegen
    0.48
    يلة
    0.47
    vagrant
    0.47
    దల
    0.46
    کنش
    0.45
    াতাড়ি
    0.45
    اق
    0.44
    Act Density 0.000%

    No Known Activations