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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .BorderFactory
    -0.07
     tiger
    -0.06
     dítě
    -0.06
     �
    -0.06
     příst
    -0.06
     gerçekten
    -0.06
    (out
    -0.06
     кож
    -0.06
    geois
    -0.06
    ために
    -0.06
    POSITIVE LOGITS
     Nur
    0.06
    ,email
    0.06
    -character
    0.06
     instruction
    0.06
     Greece
    0.06
    ح
    0.06
    worth
    0.06
     RESOURCE
    0.06
    (Request
    0.06
     sulfur
    0.06
    Act Density 0.002%

    No Known Activations