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

    Neuronpedia

    INDEX
    Explanations

    systems and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਵਾ
    0.43
    uco
    0.41
    perceptron
    0.40
     நீர்
    0.39
    ลม
    0.38
    odora
    0.38
     ምልክ
    0.38
    uasion
    0.38
    িকা
    0.38
     ชื่อ
    0.38
    POSITIVE LOGITS
     extrapolate
    0.47
     extrapol
    0.40
     afecta
    0.40
     degrad
    0.39
    Raises
    0.39
     study
    0.39
     afectan
    0.39
     degener
    0.38
     nonuniform
    0.38
     worsens
    0.37
    Act Density 0.000%

    No Known Activations