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

    Neuronpedia

    INDEX
    Explanations

    Legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shin
    -0.07
     dean
    -0.07
    ]));↵↵
    -0.07
     เส
    -0.07
    わず
    -0.07
    Senator
    -0.06
    (["
    -0.06
    ера
    -0.06
    ↵
    -0.06
    "Why
    -0.06
    POSITIVE LOGITS
     Jakarta
    0.06
     overnight
    0.06
     morphology
    0.06
     Translate
    0.06
    classified
    0.06
    ňuje
    0.06
    ilitation
    0.06
    chan
    0.06
     fatt
    0.05
    IBOutlet
    0.05
    Act Density 0.003%

    No Known Activations