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

    Neuronpedia

    INDEX
    Explanations

    terms of service violations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鿓
    0.40
     anhydride
    0.37
    quirrel
    0.37
    သေး
    0.37
    zawa
    0.37
     mammary
    0.36
    është
    0.36
    ilebilir
    0.36
    ogenies
    0.36
    물을
    0.36
    POSITIVE LOGITS
     x
    0.49
     AFM
    0.45
     доби
    0.43
     ર
    0.39
    PD
    0.39
     х
    0.39
     пробле
    0.39
    ட்ப
    0.39
     ಟ
    0.39
     complej
    0.39
    Act Density 0.001%

    No Known Activations