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

    Neuronpedia

    INDEX
    Explanations

    regular expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ktes
    -0.08
     Loh
    -0.07
     Austral
    -0.07
    ்கிற
    -0.07
    coes
    -0.07
     Lets
    -0.07
     постоянно
    -0.07
    _process
    -0.07
     venus
    -0.07
     amalg
    -0.07
    POSITIVE LOGITS
     vacances
    0.09
    0.08
    หัว
    0.08
     GTX
    0.08
     recognizable
    0.07
     jurisdiction
    0.07
    微信群
    0.07
     boîte
    0.07
    娱乐场
    0.07
    ール
    0.07
    Act Density 0.000%
    No Known Activations