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

    Neuronpedia

    INDEX
    Explanations

    assume

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     allergy
    -0.07
     rect
    -0.07
     veil
    -0.07
     royal
    -0.07
     یافت
    -0.06
     एस
    -0.06
    ější
    -0.06
     κι
    -0.06
     pepper
    -0.06
     kuvvet
    -0.06
    POSITIVE LOGITS
     assumed
    0.10
     assume
    0.10
     assumption
    0.10
     assumptions
    0.09
    assume
    0.08
     assum
    0.08
     Assuming
    0.07
     assuming
    0.07
    .Ass
    0.07
     guarante
    0.07
    Act Density 0.018%

    No Known Activations