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

    Neuronpedia

    INDEX
    Explanations

    Angular, Touching, collaborative, coffee, Sharma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Marian
    0.44
    佹
    0.42
     мнение
    0.41
     أش
    0.40
    0.40
    Jeg
    0.39
     Rockefeller
    0.39
    Passengers
    0.39
    給我
    0.39
    ಂತಹ
    0.38
    POSITIVE LOGITS
    ificaciones
    0.49
     initialise
    0.47
     terrain
    0.46
     attenuation
    0.46
     initial
    0.45
    ファイル
    0.45
     neonatal
    0.42
     inflammation
    0.42
     interface
    0.42
    画面
    0.41
    Act Density 0.007%

    No Known Activations