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

    Neuronpedia

    INDEX
    Explanations

    adjustments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sofia
    -0.06
    ちょ
    -0.06
     pipes
    -0.06
     calf
    -0.06
     Tables
    -0.06
     Rocky
    -0.06
    mf
    -0.06
     cít
    -0.06
    icts
    -0.06
     vystav
    -0.06
    POSITIVE LOGITS
    Ans
    0.07
    hung
    0.06
    _OK
    0.06
    People
    0.06
     praw
    0.06
     marketplace
    0.06
     dow
    0.06
    reur
    0.06
    .GUI
    0.06
     Wool
    0.06
    Act Density 0.014%

    No Known Activations