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

    Neuronpedia

    INDEX
    Explanations

    red flags or red herring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Augmented
    0.38
    chny
    0.37
     fusible
    0.37
    лга
    0.36
     armament
    0.36
    bica
    0.36
    隂
    0.36
     Brady
    0.36
    沌
    0.36
    磔
    0.35
    POSITIVE LOGITS
     red
    0.98
    red
    0.97
    Red
    0.97
    红
    0.91
     Red
    0.89
     레드
    0.88
    RED
    0.86
    oubt
    0.86
     赤
    0.85
    undant
    0.84
    Act Density 0.033%

    No Known Activations