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

    Neuronpedia

    INDEX
    Explanations

    code/log data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    release
    -0.06
    تی
    -0.06
    Ns
    -0.06
     После
    -0.06
    лон
    -0.06
    ця
    -0.06
     η
    -0.06
    rightness
    -0.06
     ￥
    -0.06
    .bunifuFlatButton
    -0.06
    POSITIVE LOGITS
     advisors
    0.07
     strtok
    0.07
     Interactive
    0.07
     cafeteria
    0.06
    惊
    0.06
    .res
    0.06
     exploitation
    0.06
     nhà
    0.06
     بعض
    0.06
     Thought
    0.06
    Act Density 0.753%

    No Known Activations