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

    Neuronpedia

    INDEX
    Explanations

    technical output and commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ब्ल
    0.38
     Ім
    0.38
    㘿
    0.37
    ೫
    0.37
     Lamp
    0.36
     famosa
    0.36
     praz
    0.36
     toaster
    0.36
    Lamp
    0.35
     *=
    0.35
    POSITIVE LOGITS
     arrests
    0.45
     Wellness
    0.42
    Wellness
    0.41
     leafs
    0.40
     Gesundheit
    0.40
     arrested
    0.39
     vendors
    0.39
    ্ক
    0.38
    Transformation
    0.38
     therapeut
    0.38
    Act Density 0.001%

    No Known Activations