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

    Neuronpedia

    INDEX
    Explanations

    AI, greatest, Ball, something, goat, Pepper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nus
    0.91
    𝐭
    0.88
    nol
    0.88
    nę
    0.86
    nv
    0.86
    ld
    0.85
    tes
    0.84
    amai
    0.84
    urada
    0.83
    tim
    0.82
    POSITIVE LOGITS
     nurt
    0.76
     reinforcement
    0.75
     Nutrient
    0.69
     zaht
    0.69
     Prisoner
    0.68
     hấp
    0.68
    ্ন
    0.68
     flurry
    0.68
     nutrient
    0.66
     preh
    0.66
    Act Density 0.000%

    No Known Activations