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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    没äºĭ
    -0.28
    licted
    -0.28
    avings
    -0.26
    ewan
    -0.26
     lanc
    -0.25
    _Bool
    -0.25
    è¿IJæ°Ķ
    -0.25
    leting
    -0.25
    çĶ³ãģĹ
    -0.25
     harmless
    -0.24
    POSITIVE LOGITS
    inton
    0.28
    Courier
    0.28
     PE
    0.27
     bows
    0.27
     bow
    0.26
    .sep
    0.24
     fus
    0.24
     stop
    0.24
     override
    0.24
     bul
    0.23
    Act Density 0.008%

    No Known Activations