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

    Neuronpedia

    INDEX
    Explanations

    Code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    {}
    -0.07
    ορειο
    -0.06
    ]));
↵
    -0.06
    _position
    -0.06
    tipo
    -0.06
    signal
    -0.06
     Hand
    -0.06
    -ed
    -0.06
    enerated
    -0.06
    _week
    -0.06
    POSITIVE LOGITS
    Instead
    0.07
     Lis
    0.07
     classy
    0.07
    anna
    0.07
     marketers
    0.06
     왜
    0.06
    anst
    0.06
    アメリカ
    0.06
    ême
    0.06
     bids
    0.06
    Act Density 0.000%

    No Known Activations