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

    Neuronpedia

    INDEX
    Explanations

    beyond the scope of this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ramique
    0.57
     défaut
    0.51
     abstractions
    0.50
     interesses
    0.50
    éb
    0.49
     températures
    0.48
    erté
    0.47
    osphère
    0.47
    Stud
    0.46
     opérations
    0.45
    POSITIVE LOGITS
    n
    0.44
    amp
    0.43
    嚜
    0.40
     তা
    0.40
    ње
    0.40
     들
    0.39
    嚥
    0.39
     shown
    0.39
     नंद
    0.39
    ක්ෂ
    0.38
    Act Density 0.000%

    No Known Activations