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

    Neuronpedia

    INDEX
    Explanations

    Alignment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onds
    -0.06
    $user
    -0.06
    Coder
    -0.06
    BEST
    -0.06
     Edge
    -0.06
     Clayton
    -0.06
     Auth
    -0.06
    orrar
    -0.06
    rails
    -0.06
    ength
    -0.06
    POSITIVE LOGITS
     getView
    0.08
    .rawValue
    0.07
    !"↵
    0.07
    (){}↵
    0.07
     Pe
    0.07
     Equip
    0.06
    PATCH
    0.06
     '!
    0.06
    )!↵
    0.06
     Pendant
    0.06
    Act Density 0.001%

    No Known Activations