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

    Neuronpedia

    INDEX
    Explanations

    code tokens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _REPEAT
    -0.07
    (student
    -0.06
     layouts
    -0.06
    473
    -0.06
    finally
    -0.06
    _touch
    -0.06
     Gamma
    -0.06
     worried
    -0.06
    yla
    -0.06
    .cost
    -0.06
    POSITIVE LOGITS
     Об
    0.07
    antd
    0.07
    寶
    0.07
     Classic
    0.07
     Blazers
    0.06
    ieur
    0.06
     Chiến
    0.06
    phant
    0.06
    edere
    0.06
     Bear
    0.06
    Act Density 0.092%

    No Known Activations