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

    Neuronpedia

    INDEX
    Explanations

    seemingly idyllic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lysosomes
    1.63
     attho
    1.55
    竺
    1.49
     overlooking
    1.47
    洱
    1.40
    ృష్టి
    1.39
     atth
    1.38
     observables
    1.37
     tetragonal
    1.37
     literals
    1.36
    POSITIVE LOGITS
    s
    1.41
    leşt
    0.98
    Â
    0.98
    t
    0.98
     செய்யவும்
    0.88
    、『
    0.88
    그
    0.87
    ступ
    0.87
    ка
    0.84
    €“
    0.83
    Act Density 0.000%

    No Known Activations