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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Autonomous
    -0.07
    .cpu
    -0.07
    واهد
    -0.06
     引
    -0.06
    identified
    -0.06
    Resistance
    -0.06
    >M
    -0.06
    <J
    -0.06
     уз
    -0.06
    +)/
    -0.06
    POSITIVE LOGITS
     grease
    0.07
    期待
    0.07
    PT
    0.06
    ENOMEM
    0.06
    ント
    0.06
     wastewater
    0.06
    askell
    0.06
     tượng
    0.06
     Wildlife
    0.06
     datetime
    0.06
    Act Density 0.000%

    No Known Activations