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

    Neuronpedia

    INDEX
    Explanations

    technical documentation or reports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     agriculture
    0.16
     Structured
    0.15
     Approval
    0.15
     Demographic
    0.15
     Mountain
    0.14
     certain
    0.14
     Index
    0.14
     Oscill
    0.14
     Consumer
    0.14
     hierarchical
    0.14
    POSITIVE LOGITS
    ști
    0.18
    <unused1089>
    0.16
    कह
    0.16
    <unused386>
    0.16
    стоит
    0.16
    <unused323>
    0.15
    <unused406>
    0.15
    ложи
    0.15
    łada
    0.15
    送料無料
    0.15
    Act Density 0.005%

    No Known Activations