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

    Neuronpedia

    INDEX
    Explanations

    deploying, beaches, directories, drums

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     debido
    0.46
     Due
    0.46
     डिज़ाइन
    0.44
     coyote
    0.44
    કાશ
    0.41
    ാ
    0.41
     ক্লিক
    0.41
    ací
    0.40
    ))\
    0.40
    astri
    0.40
    POSITIVE LOGITS
    Fear
    0.48
    Imagem
    0.45
    {
    0.45
    Choices
    0.45
    GW
    0.45
    Story
    0.44
    Parents
    0.44
    çado
    0.43
    Hazard
    0.43
    Arch
    0.42
    Act Density 0.000%

    No Known Activations