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

    Neuronpedia

    INDEX
    Explanations

    Code or math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chers
    -0.06
     rural
    -0.06
    vehicle
    -0.06
     loos
    -0.06
    êtes
    -0.06
    ould
    -0.06
    indle
    -0.06
     이를
    -0.06
     coloring
    -0.06
    .TypeOf
    -0.06
    POSITIVE LOGITS
     PRI
    0.07
    FUNCTION
    0.06
    (AF
    0.06
     �
    0.06
     サ
    0.06
    (diff
    0.06
    　 　 　 　 　
    0.06
    _prev
    0.06
     boğ
    0.06
    .password
    0.06
    Act Density 0.033%

    No Known Activations