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

    Neuronpedia

    INDEX
    Explanations

    boolean logic operators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ino
    0.25
    ini
    0.25
    $$\
    0.25
    var
    0.25
    ertas
    0.25
    ill
    0.25
     reddish
    0.25
     willful
    0.25
     shrewd
    0.24
     la
    0.24
    POSITIVE LOGITS
    स्तेमाल
    0.31
     purposes
    0.31
     ఇప్పటికే
    0.31
    こちら
    0.31
     অধিদপ্তর
    0.30
     тог
    0.29
     Ciebie
    0.29
    ልክ
    0.29
    सायटी
    0.29
     ಇಲ್ಲಿ
    0.29
    Act Density 0.002%

    No Known Activations