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

    Neuronpedia

    INDEX
    Explanations

    Logical statements, quantifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pyongyang
    -0.08
    PROP
    -0.07
    鄉
    -0.07
     voz
    -0.06
    رح
    -0.06
    may
    -0.06
    óż
    -0.06
     Nó
    -0.06
    userManager
    -0.06
     화
    -0.06
    POSITIVE LOGITS
     für
    0.06
    ")));
↵
    0.06
     jButton
    0.06
     catalyst
    0.06
    _)↵
    0.06
    ві
    0.06
     Schwe
    0.06
    dragon
    0.06
    めて
    0.06
     [])
    0.06
    Act Density 0.004%

    No Known Activations