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

    Neuronpedia

    INDEX
    Explanations

    minimum followed by quantities or requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Eloquent
    1.72
     bribe
    1.59
    ORE
    1.57
    辕
    1.57
    Collegamenti
    1.56
     borderline
    1.51
     ہاں
    1.49
    픈
    1.48
    ย์
    1.47
     vacated
    1.47
    POSITIVE LOGITS
    zaXR
    2.38
    ار
    2.22
    ો
    2.20
    ar
    2.11
     vậy
    2.03
    et
    2.02
    ec
    1.99
    هایی
    1.98
    های
    1.97
    ñoz
    1.97
    Act Density 0.096%

    No Known Activations