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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skł
    -0.07
     LinearGradient
    -0.07
     pg
    -0.07
     humorous
    -0.07
    itus
    -0.07
     errorMsg
    -0.06
    ⁕
    -0.06
    ategy
    -0.06
     Printing
    -0.06
    煨
    -0.06
    POSITIVE LOGITS
     Funeral
    0.07
    PEnd
    0.07
     convent
    0.07
    _;↵↵
    0.07
    是要
    0.06
    thro
    0.06
    咱
    0.06
    _blocking
    0.06
    *****↵↵
    0.06
    -light
    0.06
    Act Density 0.000%

    No Known Activations