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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Experiment
    -0.06
    єв
    -0.06
    _SW
    -0.06
    VERRIDE
    -0.06
    	sw
    -0.06
     Charger
    -0.06
    REM
    -0.05
    eid
    -0.05
    ディース
    -0.05
    ेखन
    -0.05
    POSITIVE LOGITS
     декабря
    0.07
    .Vector
    0.07
    Intro
    0.07
    …↵↵↵↵
    0.07
     Portuguese
    0.07
     condoms
    0.07
    _spot
    0.06
     translators
    0.06
     moments
    0.06
    -guide
    0.06
    Act Density 0.004%

    No Known Activations