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

    Neuronpedia

    INDEX
    Explanations

    where

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Concord
    -0.07
    Este
    -0.06
    owers
    -0.06
    نده
    -0.06
     Accordingly
    -0.06
    ?<
    -0.06
    .random
    -0.06
    oji
    -0.06
    OrderId
    -0.06
     steadfast
    -0.06
    POSITIVE LOGITS
    trys
    0.07
     discourage
    0.07
    984
    0.07
    екотор
    0.07
    brities
    0.07
     contributed
    0.06
     nied
    0.06
     ◆
    0.06
     emission
    0.06
     spontaneously
    0.06
    Act Density 0.008%

    No Known Activations