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

    Neuronpedia

    INDEX
    Explanations

    vs, if, of, than

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     frosts
    0.66
     Inhibition
    0.65
     associated
    0.65
     milled
    0.64
     covered
    0.63
     harvested
    0.62
     recounted
    0.62
     barring
    0.62
     selectable
    0.61
     rafting
    0.61
    POSITIVE LOGITS
    &-
    0.64
    -$\
    0.58
    atsiya
    0.58
    -
    0.58
    U
    0.57
    el
    0.56
    spreadsheet
    0.56
    -\\
    0.56
     പാര്‍
    0.56
    此类
    0.55
    Act Density 0.312%

    No Known Activations