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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UPPER
    -0.06
     Digital
    -0.06
    浦
    -0.06
    _EX
    -0.06
    SY
    -0.06
    .BigDecimal
    -0.06
     kesin
    -0.06
    ecz
    -0.06
     obs
    -0.06
    uf
    -0.06
    POSITIVE LOGITS
    .staff
    0.08
     stránky
    0.07
    cosystem
    0.07
    ▍▍
    0.06
     Seam
    0.06
    .ball
    0.06
    /check
    0.06
    heat
    0.06
    _Return
    0.06
    hint
    0.06
    Act Density 0.108%

    No Known Activations