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

    Neuronpedia

    INDEX
    Explanations

    exactly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imen
    -0.08
    (NUM
    -0.07
    oret
    -0.07
    time
    -0.07
    sip
    -0.07
    heck
    -0.07
    hem
    -0.07
    idd
    -0.07
     FM
    -0.07
    山
    -0.07
    POSITIVE LOGITS
     exactly
    0.08
    컁
    0.07
    _pattern
    0.07
    .labelX
    0.07
     jó
    0.07
     loyalty
    0.07
     dét
    0.06
     manifesto
    0.06
    ㉿
    0.06
    ғ
    0.06
    Act Density 0.013%

    No Known Activations