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

    Neuronpedia

    INDEX
    Explanations

    Pulses, math, and technical elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sektor
    0.40
    եկ
    0.40
    Gün
    0.39
    纷
    0.38
    준다
    0.37
     अपडेट
    0.37
    UpdateTime
    0.37
    拃
    0.37
     али
    0.37
    馴染
    0.36
    POSITIVE LOGITS
    0.42
    ମ
    0.40
    )+\
    0.39
     ask
    0.38
    onian
    0.38
     HOPE
    0.38
    geqslant
    0.37
     radiator
    0.37
     requirements
    0.37
     Ask
    0.36
    Act Density 0.032%

    No Known Activations