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
     güvenli
    -0.07
     pkt
    -0.06
    CONTROL
    -0.06
     家
    -0.06
    img
    -0.06
    addon
    -0.06
    _flash
    -0.06
     helmets
    -0.06
    ityEngine
    -0.06
    ################################################################################↵
    -0.05
    POSITIVE LOGITS
     Andre
    0.08
     Nos
    0.08
     Prescott
    0.07
     newArray
    0.07
    Facing
    0.07
     그리
    0.06
    _dense
    0.06
     cites
    0.06
    _tac
    0.06
    Navigate
    0.06
    Act Density 0.017%

    No Known Activations