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

    Neuronpedia

    INDEX
    Explanations

    base class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fragment
    -0.07
    _recipe
    -0.06
    ]+"
    -0.06
     lev
    -0.06
    //----------------------------------------------------------------
    -0.06
     junk
    -0.06
    endants
    -0.06
    ван
    -0.06
     diets
    -0.06
    )];↵↵
    -0.06
    POSITIVE LOGITS
     источ
    0.07
     Fuse
    0.07
     빨
    0.07
    攝
    0.07
     перший
    0.07
     VIN
    0.07
    Filter
    0.06
    ина
    0.06
     cutter
    0.06
    ITOR
    0.06
    Act Density 0.007%

    No Known Activations