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

    Neuronpedia

    INDEX
    Explanations

    resources listed at the end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ance
    0.43
     papier
    0.42
     Medications
    0.42
    cookie
    0.41
    ée
    0.41
     cookie
    0.41
     medication
    0.41
    𝑒
    0.41
     Flora
    0.40
     aerosol
    0.40
    POSITIVE LOGITS
     умови
    0.49
    ።
    0.47
    ।
    0.47
    ۔
    0.46
     ১ম
    0.46
     disgraceful
    0.46
    MIT
    0.46
    Turn
    0.45
    zię
    0.45
     چاہیے۔
    0.44
    Act Density 0.001%

    No Known Activations