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

    Neuronpedia

    INDEX
    Explanations

    just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crates
    -0.07
    (bodyParser
    -0.06
    428
    -0.06
     شاخ
    -0.06
     savedInstanceState
    -0.06
    _PERMISSION
    -0.06
     б
    -0.06
     dve
    -0.06
     orderBy
    -0.06
    联
    -0.06
    POSITIVE LOGITS
     therapies
    0.07
    doesn
    0.07
    —an
    0.06
     Shoulder
    0.06
    нести
    0.06
     JUST
    0.06
     recognised
    0.06
     positively
    0.06
     Toy
    0.06
     Jul
    0.06
    Act Density 0.013%

    No Known Activations