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

    Neuronpedia

    INDEX
    Explanations

    importance or ranking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     present
    -0.07
    Jones
    -0.07
    .features
    -0.06
     but
    -0.06
     Độ
    -0.06
     counts
    -0.06
     Кам
    -0.06
     Uns
    -0.06
    'L
    -0.06
     Gon
    -0.06
    POSITIVE LOGITS
    sla
    0.06
    をお
    0.06
    ReturnValue
    0.06
    DELAY
    0.06
     kilometers
    0.06
     gigg
    0.06
    シャル
    0.06
     Assumes
    0.06
    udden
    0.06
     ccp
    0.06
    Act Density 0.040%

    No Known Activations