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

    Neuronpedia

    INDEX
    Explanations

    closing this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ovation
    0.37
     picnics
    0.35
     barges
    0.31
     overd
    0.31
     cervical
    0.29
    instant
    0.29
     tacos
    0.29
     cures
    0.29
     syringes
    0.29
     puns
    0.29
    POSITIVE LOGITS
    说明
    0.32
    তরাং
    0.30
    信息
    0.29
    ujourd
    0.29
     меку
    0.29
    鋆
    0.27
     முது
    0.27
    יה
    0.26
    瑢
    0.26
    Sis
    0.26
    Act Density 0.000%

    No Known Activations