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

    Neuronpedia

    INDEX
    Explanations

    say "р" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     virt
    -0.09
    Ling
    -0.08
     lumea
    -0.08
    _LINES
    -0.08
     VID
    -0.08
     maail
    -0.08
     investigação
    -0.08
     Untersuchung
    -0.08
     världen
    -0.08
     Gund
    -0.08
    POSITIVE LOGITS
    clusive
    0.09
    oxid
    0.08
    charges
    0.08
    rach
    0.07
    ilium
    0.07
    0.07
    italize
    0.07
    rik
    0.07
     ات
    0.07
    ox
    0.07
    Act Density 0.000%
    No Known Activations