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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ng
    -0.07
    AWS
    -0.07
     Extract
    -0.07
    =float
    -0.06
     भव
    -0.06
    .multiply
    -0.06
     Matt
    -0.06
    лев
    -0.06
     hunted
    -0.06
     engines
    -0.06
    POSITIVE LOGITS
     　　　　　　
    0.08
     Acrobat
    0.07
     rady
    0.06
     　　　　
    0.06
    :::::
    0.06
     　　　　　　　
    0.06
     discovery
    0.06
     　　 　
    0.06
    ظام
    0.06
    .RE
    0.06
    Act Density 0.018%

    No Known Activations