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

    Neuronpedia

    INDEX
    Explanations

    Analytic Philosophy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     an
    0.61
     yellow
    0.59
     trailing
    0.57
     catamaran
    0.55
     final
    0.54
     def
    0.54
     invalid
    0.52
     my
    0.51
     blue
    0.51
     kam
    0.51
    POSITIVE LOGITS
    𝕙
    0.57
    Estab
    0.52
    ATL
    0.51
     ದಾ
    0.51
     vaisse
    0.49
     rozd
    0.49
    મ
    0.49
    ĐT
    0.49
    HLA
    0.49
     받았
    0.48
    Act Density 0.000%

    No Known Activations