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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    612
    -0.06
    _nat
    -0.06
     ",
↵
    -0.06
    },'
    -0.06
    _hz
    -0.06
     Jame
    -0.06
     начинает
    -0.06
    (fid
    -0.06
     proposed
    -0.06
    Emitter
    -0.06
    POSITIVE LOGITS
     constexpr
    0.07
     ча
    0.07
     Gand
    0.07
    .BO
    0.07
    .Enter
    0.06
    ация
    0.06
     autop
    0.06
    ISTRIBUT
    0.06
     Sens
    0.06
     chị
    0.06
    Act Density 0.097%

    No Known Activations