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

    Neuronpedia

    INDEX
    Explanations

    code or data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Expired
    -0.07
     Spending
    -0.06
    ccd
    -0.06
     RD
    -0.06
     organise
    -0.06
    руч
    -0.06
     ใช
    -0.06
     чит
    -0.06
     CIF
    -0.06
    .nextLine
    -0.06
    POSITIVE LOGITS
    ダー
    0.07
    akedown
    0.06
    목
    0.06
     finally
    0.06
     shemale
    0.06
     unnatural
    0.06
    _entropy
    0.06
    finally
    0.06
     añ
    0.06
     greatness
    0.06
    Act Density 0.014%

    No Known Activations