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

    Neuronpedia

    INDEX
    Explanations

    claim and verify keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    develop
    0.47
     služ
    0.46
     Soviet
    0.46
    insurance
    0.42
     hotels
    0.41
     incorpor
    0.41
     Republike
    0.40
     zakup
    0.40
     නිෂ්පා
    0.40
    ᐛ
    0.40
    POSITIVE LOGITS
     ಹಲ
    0.44
     በት
    0.41
    ማሪ
    0.39
     keywords
    0.39
     Student
    0.38
    izzando
    0.38
    覃
    0.37
    टि
    0.37
    鹸
    0.37
    Sun
    0.37
    Act Density 0.005%

    No Known Activations