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

    Neuronpedia

    INDEX
    Explanations

    years or dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plenty
    0.43
     the
    0.42
     flimsy
    0.41
     ragged
    0.40
     gooey
    0.39
     delusions
    0.38
     nineteenth
    0.38
     debatable
    0.38
     shady
    0.38
    НЫ
    0.38
    POSITIVE LOGITS
    。
    0.49
    ។
    0.47
    。”
    0.41
    期間
    0.40
    time
    0.39
    ։
    0.38
    ®.
    0.38
    ،
    0.38
    .,
    0.37
     ነበር
    0.37
    Act Density 0.020%

    No Known Activations