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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intox
    -0.07
     transmission
    -0.07
     CAMERA
    -0.07
    (part
    -0.07
    概
    -0.07
    ACCEPT
    -0.06
     scrambling
    -0.06
    🥶
    -0.06
    汇总
    -0.06
     pointer
    -0.06
    POSITIVE LOGITS
     habitats
    0.08
    皇宫
    0.08
     hungry
    0.07
     ammunition
    0.07
     dealing
    0.07
    ły
    0.07
     turbines
    0.07
     USD
    0.07
    shots
    0.07
    ates
    0.07
    Act Density 0.002%

    No Known Activations