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

    Neuronpedia

    INDEX
    Explanations

    reaching limits or levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Etat
    0.46
    finger
    0.44
     골
    0.44
    ^{*}$.
    0.43
    niku
    0.43
    ermodel
    0.42
    myItem
    0.42
    igma
    0.42
    Equals
    0.42
    flower
    0.41
    POSITIVE LOGITS
     spreadsheets
    0.50
     orchards
    0.47
     charts
    0.46
     cuttings
    0.45
     gearing
    0.44
     infections
    0.44
     NCR
    0.43
     reim
    0.42
     Largo
    0.42
     fills
    0.42
    Act Density 0.005%

    No Known Activations