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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Question
    -0.07
     Learning
    -0.07
    rière
    -0.07
    substring
    -0.06
    Diff
    -0.06
     embedding
    -0.06
     reasoning
    -0.06
     beforeEach
    -0.06
    imp
    -0.06
     인
    -0.06
    POSITIVE LOGITS
    集市
    0.07
    /games
    0.07
    "]=$
    0.07
     >",
    0.07
    .maps
    0.07
     שת
    0.07
    样式
    0.06
     Pear
    0.06
    畋
    0.06
    [attr
    0.06
    Act Density 0.029%

    No Known Activations