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

    Neuronpedia

    INDEX
    Explanations

    additional funding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PE
    0.94
     PC
    0.91
     Allen
    0.90
     Allan
    0.89
    Meyer
    0.86
     Meyer
    0.86
     PEG
    0.84
     Vail
    0.83
     Herman
    0.80
     Pe
    0.80
    POSITIVE LOGITS
     Blackmore
    1.05
    <0xA0>
    1.02
     Strath
    0.99
     الأس
    0.97
    阉
    0.94
    リュ
    0.92
    Estr
    0.91
     Ак
    0.91
     Struggles
    0.91
     Brant
    0.90
    Act Density 2.794%

    No Known Activations