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

    Neuronpedia

    INDEX
    Explanations

    text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     planets
    -0.07
    oğraf
    -0.06
    .maven
    -0.06
     ngồi
    -0.06
     Dt
    -0.06
    iece
    -0.06
     تست
    -0.06
    ус
    -0.06
     rowNum
    -0.06
     tego
    -0.06
    POSITIVE LOGITS
    _join
    0.07
    belief
    0.06
     abdominal
    0.06
     gradient
    0.06
     Titles
    0.06
    (bottom
    0.06
     amplify
    0.06
    Send
    0.06
     Constants
    0.06
    (Resources
    0.06
    Act Density 0.167%

    No Known Activations