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

    Neuronpedia

    INDEX
    Explanations

    tokens that represent numbers with unicode characters present

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pazar
    -0.06
    ặn
    -0.06
    ograd
    -0.06
     Orta
    -0.06
    ứng
    -0.06
    lag
    -0.06
    fel
    -0.06
    lagen
    -0.06
     otherwise
    -0.05
    rieb
    -0.05
    POSITIVE LOGITS
    /or
    0.07
    omen
    0.06
     RuntimeMethod
    0.06
    enso
    0.06
    ignKey
    0.06
    avit
    0.06
    itzer
    0.06
    MBProgressHUD
    0.06
    ONTAL
    0.06
    ESSAGE
    0.06
    Act Density 0.272%

    No Known Activations