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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eru
    -0.07
    アップ
    -0.07
    ать
    -0.07
    dock
    -0.07
    atars
    -0.06
    опас
    -0.06
     υπηρε
    -0.06
    +self
    -0.06
    omen
    -0.06
    oder
    -0.06
    POSITIVE LOGITS
     aday
    0.06
    =batch
    0.06
    	Value
    0.06
     genuinely
    0.06
    //================================================
    0.06
    ]?
    0.06
     #↵
    0.06
     Escort
    0.06
     {!
    0.06
    >'
↵
    0.06
    Act Density 0.000%

    No Known Activations