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

    Neuronpedia

    INDEX
    Explanations

    text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ngữ
    -0.06
     �
    -0.06
    doctrine
    -0.06
    sensor
    -0.06
    //@
    -0.06
     Fou
    -0.06
    cq
    -0.06
    ysics
    -0.06
    cheme
    -0.05
    pace
    -0.05
    POSITIVE LOGITS
     foam
    0.07
     Sergeant
    0.07
     remember
    0.06
    unger
    0.06
    .raise
    0.06
    ewan
    0.06
     tit
    0.06
     chai
    0.06
     PIXI
    0.06
    underscore
    0.06
    Act Density 0.000%

    No Known Activations