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

    Neuronpedia

    INDEX
    Explanations

    "It" or "this" followed by a verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    json
    0.48
     όλα
    0.47
    mysqli
    0.46
    𝜃
    0.45
    最初の
    0.44
    everything
    0.42
     ()=>{
    0.42
     모든
    0.42
    retti
    0.42
    INITIAL
    0.42
    POSITIVE LOGITS
     to
    0.47
     Back
    0.47
     stewards
    0.46
    蜮
    0.46
     légère
    0.46
     on
    0.45
     a
    0.45
     Garner
    0.44
     debated
    0.43
     an
    0.43
    Act Density 0.003%

    No Known Activations