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

    Neuronpedia

    INDEX
    Explanations

    ==

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bole
    -0.07
    .BLUE
    -0.07
    蘇
    -0.06
     εξ
    -0.06
    .mu
    -0.06
    artisanlib
    -0.06
    rances
    -0.06
    bia
    -0.06
    $
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    .fac
    0.07
    οκ
    0.06
     Hp
    0.06
    ующ
    0.06
     Saskatchewan
    0.06
    BILL
    0.06
    /autoload
    0.06
    лось
    0.06
     Steven
    0.06
     stderr
    0.06
    Act Density 0.001%

    No Known Activations