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

    Neuronpedia

    INDEX
    Explanations

    Destination

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     redistribution
    -0.07
    FindObject
    -0.06
    (include
    -0.06
    _fh
    -0.06
     Wag
    -0.06
     tease
    -0.06
    scp
    -0.06
     jury
    -0.06
     psz
    -0.06
    fact
    -0.06
    POSITIVE LOGITS
    эй
    0.06
     cigarette
    0.06
    елей
    0.06
     Cob
    0.06
    لاة
    0.06
    .Matrix
    0.06
    超过
    0.06
     Stella
    0.06
     Tested
    0.06
    AN
    0.06
    Act Density 0.044%

    No Known Activations