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

    Neuronpedia

    INDEX
    Explanations

    comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     측
    -0.07
     Holder
    -0.07
     arr
    -0.06
    596
    -0.06
     harm
    -0.06
    只要
    -0.06
     "/
    -0.06
    导致
    -0.06
     bend
    -0.06
     investigators
    -0.06
    POSITIVE LOGITS
    LOUD
    0.06
     trie
    0.06
    .XtraEditors
    0.06
    pekt
    0.06
     Diy
    0.06
    games
    0.06
    deş
    0.06
     Inform
    0.06
    -serving
    0.06
    ист
    0.06
    Act Density 0.042%

    No Known Activations