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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Louis
    -0.06
     davidjl
    -0.06
     mathematics
    -0.06
    래스
    -0.06
    ி
    -0.06
    sterdam
    -0.06
     deterior
    -0.06
     Estado
    -0.06
     Passive
    -0.06
    -result
    -0.06
    POSITIVE LOGITS
    pulse
    0.07
    .gamma
    0.07
    ucz
    0.07
    бу
    0.07
     mocker
    0.07
    -↵↵
    0.07
    -call
    0.06
    '",↵
    0.06
    !");↵↵
    0.06
    843
    0.06
    Act Density 0.000%

    No Known Activations