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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Canary
    -0.07
     stacks
    -0.07
     bang
    -0.06
     drastic
    -0.06
     )->
    -0.06
    速度
    -0.06
     xb
    -0.06
     bab
    -0.06
     VB
    -0.06
    hta
    -0.06
    POSITIVE LOGITS
     journalism
    0.07
     ترکی
    0.07
     ‎#
    0.07
     người
    0.07
    ا
    0.06
    ιχ
    0.06
    олот
    0.06
     disillusion
    0.06
    Lorem
    0.06
    irlines
    0.06
    Act Density 0.004%

    No Known Activations