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

    Neuronpedia

    INDEX
    Explanations

    Quotes, titles, examples

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
     subsidiaries
    -0.07
     рецеп
    -0.07
     cousins
    -0.07
     pec
    -0.06
     prést
    -0.06
    מיטב
    -0.06
    سهل
    -0.06
    ’am
    -0.06
     guarante
    -0.06
    參與
    -0.06
    POSITIVE LOGITS
    _movement
    0.07
     פו
    0.07
     cycling
    0.06
     Import
    0.06
    slot
    0.06
    _initialized
    0.06
    otion
    0.06
    /column
    0.06
    .python
    0.06
    прос
    0.06
    Act Density 0.049%

    No Known Activations