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

    Neuronpedia

    INDEX
    Explanations

    quadratic equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     хат
    -0.10
     pitkä
    -0.08
     Patrice
    -0.08
     Dynasty
    -0.08
     transactional
    -0.08
     listar
    -0.08
     fosse
    -0.08
     dynamique
    -0.08
     reclam
    -0.08
     gait
    -0.08
    POSITIVE LOGITS
     discrimin
    0.09
    .Condition
    0.08
     sufficient
    0.08
     existence
    0.08
    Condition
    0.08
     diskr
    0.07
     condition
    0.07
     CONDITION
    0.07
    判
    0.07
    íme
    0.07
    Act Density 0.041%

    No Known Activations