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

    Neuronpedia

    INDEX
    Explanations

    winners

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     strokeLine
    -0.07
    ยา
    -0.06
     misrepresented
    -0.06
     rx
    -0.06
    這
    -0.06
    žila
    -0.06
    getDate
    -0.06
    sum
    -0.05
    .drawer
    -0.05
    rální
    -0.05
    POSITIVE LOGITS
     encourage
    0.07
    _Version
    0.07
     rearr
    0.07
     đáp
    0.07
     CELL
    0.07
     brochure
    0.07
     нерв
    0.07
    HAVE
    0.06
     Rodriguez
    0.06
    IENCE
    0.06
    Act Density 0.008%

    No Known Activations