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

    Neuronpedia

    INDEX
    Explanations

    website/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ге
    -0.07
    Cost
    -0.07
    Messages
    -0.07
    effective
    -0.06
    Offers
    -0.06
    mall
    -0.06
     heaven
    -0.06
     unquestion
    -0.06
    	size
    -0.06
    -resolution
    -0.06
    POSITIVE LOGITS
    ([]*
    0.07
     bd
    0.06
     Zá
    0.06
    Freq
    0.06
    坛
    0.06
     &(
    0.06
     kazanç
    0.06
    σφ
    0.06
     omn
    0.06
     всп
    0.06
    Act Density 0.148%

    No Known Activations