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

    Neuronpedia

    INDEX
    Explanations

    background

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parental
    -0.07
     itens
    -0.07
    coln
    -0.07
     Anatomy
    -0.07
     조
    -0.07
     ess
    -0.07
     teknik
    -0.07
    .container
    -0.06
    (pe
    -0.06
     Ce
    -0.06
    POSITIVE LOGITS
    apollo
    0.06
    background
    0.06
    <Mesh
    0.06
     research
    0.06
    Requires
    0.06
    yeah
    0.06
    город
    0.06
     keyst
    0.06
    чить
    0.06
    اشی
    0.05
    Act Density 0.002%

    No Known Activations