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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    互
    -0.07
     Redemption
    -0.06
    ，当
    -0.06
     ROAD
    -0.06
     machine
    -0.06
     assim
    -0.06
     Mall
    -0.06
    воз
    -0.06
     monks
    -0.06
     Bias
    -0.06
    POSITIVE LOGITS
     serde
    0.07
    葉
    0.07
    Passwords
    0.06
     سازمان
    0.06
    Title
    0.06
    778
    0.06
    roducing
    0.06
     bölüm
    0.06
    Finish
    0.06
    /groups
    0.06
    Act Density 0.000%

    No Known Activations