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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Char
    -0.08
    _MODULES
    -0.07
    ואה
    -0.07
    Cons
    -0.07
    ))))
    -0.07
    ))),
    -0.07
     לבחור
    -0.07
    صول
    -0.07
    "<?
    -0.07
    .body
    -0.07
    POSITIVE LOGITS
    NW
    0.07
     stays
    0.07
     Selling
    0.07
     Brent
    0.07
    imension
    0.07
     debug
    0.06
    wit
    0.06
     Cognitive
    0.06
     miłości
    0.06
    修炼
    0.06
    Act Density 0.006%

    No Known Activations