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

    Neuronpedia

    INDEX
    Explanations

    say very

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ve
    0.52
    Ve
    0.50
    VE
    0.46
    we
    0.46
    ве
    0.45
     Ve
    0.44
    se
    0.43
    vez
    0.39
    RM
    0.39
    BZ
    0.39
    POSITIVE LOGITS
    อรี่
    0.48
    িয়
    0.40
    ূট
    0.40
    iary
    0.40
     Concerto
    0.39
     ary
    0.38
     Carrie
    0.38
    ॉयड
    0.38
    aien
    0.38
    uffy
    0.37
    Act Density 0.002%

    No Known Activations