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

    Neuronpedia

    INDEX
    Explanations

    position

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yan
    -0.07
    lat
    -0.07
    채
    -0.06
    -0.06
    cep
    -0.06
    ")↵
    -0.06
    /pr
    -0.06
    anc
    -0.06
    idae
    -0.06
    在
    -0.06
    POSITIVE LOGITS
     Griffith
    0.07
     Rib
    0.07
     Таким
    0.06
    retch
    0.06
    675
    0.06
     독
    0.06
     brasile
    0.06
     sluts
    0.06
     Alternatively
    0.06
     smack
    0.06
    Act Density 0.000%

    No Known Activations