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

    Neuronpedia

    INDEX
    Explanations

    that/is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tox
    -0.07
    εβ
    -0.07
    ード
    -0.06
     화
    -0.06
     ellas
    -0.06
     �
    -0.06
    _bullet
    -0.06
    لع
    -0.06
     ebx
    -0.06
     CFG
    -0.06
    POSITIVE LOGITS
    ruby
    0.07
     fie
    0.07
    iete
    0.07
    iver
    0.07
    Amt
    0.06
    řízení
    0.06
    chte
    0.06
     iris
    0.06
     Target
    0.06
    adius
    0.06
    Act Density 0.026%

    No Known Activations