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

    Neuronpedia

    INDEX
    Explanations

    revealing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Feed
    -0.06
    _AG
    -0.06
     روند
    -0.06
    .Trim
    -0.06
     Shed
    -0.06
    -Ta
    -0.06
     노
    -0.06
    (Tile
    -0.06
    어가
    -0.06
     cole
    -0.06
    POSITIVE LOGITS
     sach
    0.07
     skillet
    0.07
     resume
    0.07
    -memory
    0.07
    OPSIS
    0.06
     Samuel
    0.06
    DTV
    0.06
    .")↵↵
    0.06
    Bitcoin
    0.06
    .master
    0.06
    Act Density 0.007%

    No Known Activations