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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    malloc
    -0.07
    Recv
    -0.07
    ADS
    -0.06
    Hack
    -0.06
     Alpha
    -0.06
     �
    -0.06
    oot
    -0.06
     처리
    -0.06
    UGC
    -0.06
    מצרים
    -0.06
    POSITIVE LOGITS
    +p
    0.07
     injuring
    0.07
    .LayoutInflater
    0.07
    岁的
    0.07
    	and
    0.07
     kitchen
    0.07
     rapport
    0.07
    %',
    0.07
    温和
    0.07
    独立
    0.07
    Act Density 0.037%

    No Known Activations