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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gover
    -0.06
     듯
    -0.06
     ntohs
    -0.06
    (skb
    -0.06
     euth
    -0.06
     hvor
    -0.06
     trainers
    -0.06
    .Real
    -0.06
    '");↵
    -0.06
    $total
    -0.06
    POSITIVE LOGITS
    大全
    0.07
    فال
    0.07
    не
    0.06
    고
    0.06
     san
    0.06
    Pale
    0.06
    нак
    0.06
    -city
    0.06
    ()/
    0.06
    -drive
    0.06
    Act Density 0.027%

    No Known Activations