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

    Neuronpedia

    INDEX
    Explanations

    various applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    c
    0.96
    p
    0.91
    ad
    0.82
    ל
    0.81
    til
    0.79
    t
    0.78
    l
    0.77
    イク
    0.76
    in
    0.76
    tit
    0.74
    POSITIVE LOGITS
     mittels
    0.87
     verschiedene
    0.78
     mehrere
    0.74
     lecz
    0.72
     estándar
    0.70
    するための
    0.70
     aspetti
    0.69
    :
    0.68
     związ
    0.68
    めん
    0.68
    Act Density 0.293%

    No Known Activations