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

    Neuronpedia

    INDEX
    Explanations

    past tense actions completed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abatic
    0.44
    Derek
    0.42
    ös
    0.42
    addGap
    0.41
    haired
    0.40
    able
    0.39
    үнд
    0.39
    kelijke
    0.38
     idée
    0.38
    zPosition
    0.38
    POSITIVE LOGITS
    ness
    0.54
     goods
    0.51
    ependent
    0.50
    त
    0.49
     recientemente
    0.48
     versions
    0.47
    व
    0.47
     нами
    0.47
    ನಲ್ಲಿ
    0.46
    ت
    0.46
    Act Density 0.085%

    No Known Activations