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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IMUM
    -0.08
    (GPIO
    -0.07
    ARRANT
    -0.07
    所致
    -0.06
    .Form
    -0.06
    dynamic
    -0.06
     Zimmerman
    -0.06
    Ṡ
    -0.06
     chip
    -0.06
    为导向
    -0.06
    POSITIVE LOGITS
     parses
    0.08
    _
↵
    0.07
     евр
    0.07
    grad
    0.07
    _mod
    0.07
    .gold
    0.06
     modelAndView
    0.06
     Moves
    0.06
     Lara
    0.06
     каз
    0.06
    Act Density 0.031%

    No Known Activations