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

    Neuronpedia

    INDEX
    Explanations

    common word beginnings and endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    перь
    1.32
    cellaneous
    1.25
    újo
    1.24
     quilt
    1.24
    ²
    1.21
    которые
    1.17
    RNAs
    1.16
     taxon
    1.14
     renormal
    1.14
     figlio
    1.12
    POSITIVE LOGITS
    ра
    1.73
    stood
    1.52
    רות
    1.50
    cknowled
    1.50
    u
    1.43
    ו
    1.40
    ed
    1.37
    an
    1.36
    lapping
    1.35
    jenigen
    1.31
    Act Density 0.808%

    No Known Activations