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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Transaction
    -0.07
    Numeric
    -0.07
     horas
    -0.06
     ध
    -0.06
    thest
    -0.06
    Attachments
    -0.06
    _VLAN
    -0.06
    (flow
    -0.06
    iah
    -0.06
    _vert
    -0.06
    POSITIVE LOGITS
     ASF
    0.07
     Approx
    0.06
     Quant
    0.06
    sizlik
    0.06
    .diag
    0.06
    _payment
    0.06
    Cong
    0.06
     Eag
    0.06
     Shopify
    0.06
    unsqueeze
    0.06
    Act Density 0.055%

    No Known Activations