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

    Neuronpedia

    INDEX
    Explanations

    commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ({
    -0.07
    orton
    -0.07
    .ToDateTime
    -0.07
    _components
    -0.06
    iator
    -0.06
    周期
    -0.06
    igrant
    -0.06
     mouseClicked
    -0.06
    386
    -0.06
     PreparedStatement
    -0.06
    POSITIVE LOGITS
     Markdown
    0.06
     SEG
    0.06
     delightful
    0.06
     earnest
    0.06
    أم
    0.05
     Christopher
    0.05
     ní
    0.05
    religious
    0.05
    ATAR
    0.05
    alysis
    0.05
    Act Density 0.063%

    No Known Activations