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

    Neuronpedia

    INDEX
    Explanations

    punctuation or code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    South
    0.70
     constitute
    0.70
     obviously
    0.70
    English
    0.69
     automatically
    0.68
     firstly
    0.66
     conversely
    0.66
     probably
    0.65
     considered
    0.65
    Portugal
    0.65
    POSITIVE LOGITS
    .",
    0.79
    \%.
    0.73
    ,"
    0.72
    ."
    0.69
    .},
    0.68
    +".
    0.66
    ,'"
    0.66
    /",
    0.65
    ".
    0.65
    ]",
    0.64
    Act Density 0.000%

    No Known Activations