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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     baff
    -0.07
     filters
    -0.06
     Monday
    -0.06
     support
    -0.06
    ())↵↵
    -0.06
     tabs
    -0.06
     Compatible
    -0.06
    -The
    -0.06
     Alignment
    -0.06
     Friendly
    -0.06
    POSITIVE LOGITS
     шк
    0.07
     objeto
    0.07
     beim
    0.07
    .vx
    0.07
     overarching
    0.06
    vably
    0.06
    _loaded
    0.06
    .vote
    0.06
    enez
    0.06
    exemple
    0.06
    Act Density 0.060%

    No Known Activations