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

    Neuronpedia

    INDEX
    Explanations

    common multiples/factors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     equivalent
    -0.07
    .logs
    -0.07
     microtime
    -0.07
     violated
    -0.07
     Arab
    -0.07
    .f
    -0.07
     الداخ
    -0.07
    .FALSE
    -0.06
    那
    -0.06
    Lat
    -0.06
    POSITIVE LOGITS
    Container
    0.06
     disarm
    0.06
    ',{↵
    0.06
    Usu
    0.06
     Maria
    0.06
    Material
    0.06
    .Map
    0.06
    .spacing
    0.06
    ypo
    0.06
    Gal
    0.05
    Act Density 0.008%

    No Known Activations