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

    Neuronpedia

    INDEX
    Explanations

    Turing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     अर
    -0.07
    _loss
    -0.06
    руют
    -0.06
    ?>>↵
    -0.06
    орош
    -0.06
    onal
    -0.06
     anomalies
    -0.06
    vre
    -0.06
     Barr
    -0.06
    ่อต
    -0.06
    POSITIVE LOGITS
     Turing
    0.18
    ping
    0.07
     bid
    0.07
    urable
    0.07
     burg
    0.06
    ;amp
    0.06
     případě
    0.06
    =True
    0.06
    vim
    0.06
    ancellation
    0.06
    Act Density 0.000%

    No Known Activations