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

    Neuronpedia

    INDEX
    Explanations

    independent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sorted
    -0.07
    Boss
    -0.06
    <data
    -0.06
    attles
    -0.06
    commands
    -0.06
     lobbyist
    -0.06
    _elt
    -0.06
     medic
    -0.06
     feliz
    -0.06
     منظور
    -0.06
    POSITIVE LOGITS
     "",
↵
    0.07
    /be
    0.07
     додатков
    0.07
     ک
    0.07
     หม
    0.07
     Ranger
    0.07
    !",↵
    0.07
     %#
    0.06
    .Drawable
    0.06
     أخ
    0.06
    Act Density 0.005%

    No Known Activations