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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Service
    -0.06
    _TAC
    -0.06
     бу
    -0.06
     Pop
    -0.06
     WOW
    -0.06
    (Response
    -0.06
     offset
    -0.06
    .throw
    -0.06
     ACA
    -0.06
     Sty
    -0.06
    POSITIVE LOGITS
    =";↵
    0.07
    _PASSWORD
    0.06
    _CHAR
    0.06
    _firstname
    0.06
    iveau
    0.06
     دولتی
    0.06
    .BindingSource
    0.06
     пропози
    0.06
     agli
    0.06
     à
    0.06
    Act Density 0.077%

    No Known Activations