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

    Neuronpedia

    INDEX
    Explanations

    useEffect hooks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     erroneously
    0.44
     correspondingly
    0.40
     provocative
    0.39
     optimizations
    0.39
    osar
    0.38
     Agree
    0.38
     analysis
    0.38
     publicized
    0.38
    ವರೆ
    0.37
     somebody
    0.37
    POSITIVE LOGITS
    μά
    0.44
    ιδ
    0.43
    τσ
    0.40
    male
    0.40
    Fleet
    0.39
    恹
    0.39
    MOT
    0.39
    )
    0.38
    ίν
    0.38
    ת
    0.38
    Act Density 0.001%

    No Known Activations