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

    Neuronpedia

    INDEX
    Explanations

    Bullet points and formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    elu
    -0.07
    ark
    -0.07
    zed
    -0.07
     bisc
    -0.07
     digging
    -0.07
    arks
    -0.07
    Cant
    -0.07
    ırs
    -0.07
    �
    -0.07
     cant
    -0.07
    POSITIVE LOGITS
     qualifies
    0.09
     criteria
    0.09
    Criteria
    0.08
     kriter
    0.08
     criterios
    0.08
     критер
    0.08
    .qual
    0.08
    Typically
    0.08
     critérios
    0.08
     definição
    0.08
    Act Density 0.041%

    No Known Activations