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

    Neuronpedia

    INDEX
    Explanations

    ratios

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     měst
    -0.07
     emperor
    -0.07
    _set
    -0.07
    -runner
    -0.07
    (duration
    -0.06
    terdam
    -0.06
    STER
    -0.06
     νεφοκ
    -0.06
    navbarSupportedContent
    -0.06
     Rigidbody
    -0.06
    POSITIVE LOGITS
     endangered
    0.06
    243
    0.06
     Angeles
    0.06
     Tex
    0.06
     accommodations
    0.06
     пам
    0.06
    _SH
    0.06
    _home
    0.06
     cin
    0.06
    �
    0.06
    Act Density 0.000%

    No Known Activations