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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	diff
    -0.06
    oment
    -0.06
    owed
    -0.06
     VIC
    -0.06
    .Ass
    -0.06
     iam
    -0.06
    Bro
    -0.06
     mercenaries
    -0.06
     Month
    -0.06
     bombers
    -0.06
    POSITIVE LOGITS
    .innerWidth
    0.06
     unreasonable
    0.06
    _BACKGROUND
    0.06
    ければ
    0.06
     baker
    0.06
    ़ें
    0.06
    !!↵↵
    0.06
     grup
    0.06
     Molecular
    0.06
    에게
    0.06
    Act Density 0.004%

    No Known Activations