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

    Neuronpedia

    INDEX
    Explanations

    rates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    بن
    -0.07
     tears
    -0.06
    _doc
    -0.06
    anny
    -0.06
     layer
    -0.06
    协
    -0.06
    .note
    -0.06
    ollapsed
    -0.06
    atar
    -0.06
     sightings
    -0.06
    POSITIVE LOGITS
    _FIX
    0.07
    ToFront
    0.07
    _abstract
    0.07
     Geld
    0.06
    ソ
    0.06
    Recovered
    0.06
     inconsist
    0.06
    -ticket
    0.06
    _gb
    0.06
    bt
    0.06
    Act Density 0.018%

    No Known Activations