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

    Neuronpedia

    INDEX
    Explanations

    strengthening feelings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    byter
    -0.07
     Pay
    -0.06
     Cheat
    -0.06
    ْه
    -0.06
     Fro
    -0.06
    .setViewportView
    -0.06
    Fund
    -0.06
    Eth
    -0.06
    Mel
    -0.06
     Attempt
    -0.06
    POSITIVE LOGITS
     discrepan
    0.08
    简单
    0.07
     欧
    0.07
    差
    0.06
     schop
    0.06
     Spurs
    0.06
     JFrame
    0.06
    parts
    0.06
    ，便
    0.06
     cc
    0.06
    Act Density 0.013%

    No Known Activations