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

    Neuronpedia

    INDEX
    Explanations

    finding "what"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bands
    0.45
    âteaux
    0.45
     പൊ
    0.45
     ⚫
    0.44
    设计的
    0.44
    Designs
    0.44
    band
    0.43
    aves
    0.43
    CHT
    0.43
     aplicações
    0.42
    POSITIVE LOGITS
     Sperm
    0.49
     Wage
    0.45
    ਸੀ
    0.43
    itarian
    0.43
    سپ
    0.43
     Sill
    0.43
     Defense
    0.42
    کسی
    0.42
     Training
    0.41
    ян
    0.41
    Act Density 0.004%

    No Known Activations