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

    Neuronpedia

    INDEX
    Explanations

    code/API keys/strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "is
    -0.07
    .favorite
    -0.06
    terminal
    -0.06
    科
    -0.06
     cheer
    -0.06
    Õ
    -0.06
     protože
    -0.06
    eated
    -0.06
    ,is
    -0.06
    _DISK
    -0.06
    POSITIVE LOGITS
     recruiting
    0.07
    $s
    0.07
    /react
    0.07
    reten
    0.07
     пор
    0.07
     SMS
    0.06
     HQ
    0.06
     giriş
    0.06
     mov
    0.06
     rs
    0.06
    Act Density 0.194%

    No Known Activations