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
     initiator
    -0.07
    orney
    -0.06
     Biological
    -0.06
     installment
    -0.05
    UME
    -0.05
    �
    -0.05
    �
    -0.05
    QUOTE
    -0.05
     �
    -0.05
    .signals
    -0.05
    POSITIVE LOGITS
    ()`
    0.08
    懂
    0.07
     blob
    0.07
    /Data
    0.07
    >",
    0.07
    fty
    0.07
    상품
    0.07
    etsy
    0.07
    ihil
    0.07
    emoc
    0.07
    Act Density 0.000%

    No Known Activations