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

    Neuronpedia

    INDEX
    Explanations

    technical terms and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Henderson
    0.33
    Campbell
    0.32
    toilet
    0.30
     steeple
    0.30
     Campbell
    0.29
     simonsen
    0.29
    Pine
    0.29
    burgh
    0.29
    itts
    0.29
    church
    0.28
    POSITIVE LOGITS
    ，
    0.40
     Hadoop
    0.36
     immutable
    0.35
     initialized
    0.35
     /*
    0.34
     Metadata
    0.34
     Debug
    0.33
     echoed
    0.33
     Unicode
    0.33
     recursively
    0.32
    Act Density 0.001%

    No Known Activations