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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "@/
    -0.06
    addOn
    -0.06
    897
    -0.06
    *>*
    -0.06
     Ό
    -0.06
     حضرت
    -0.06
     ###↵
    -0.06
     Trap
    -0.06
    よく
    -0.06
     หล
    -0.06
    POSITIVE LOGITS
     nakonec
    0.07
     Programming
    0.07
     posed
    0.07
    (ms
    0.06
    aturated
    0.06
    amento
    0.06
     wes
    0.06
    fred
    0.06
    ep
    0.06
    sequ
    0.06
    Act Density 0.012%

    No Known Activations