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

    Neuronpedia

    INDEX
    Explanations

    Index CPI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pron
    0.42
     pron
    0.42
    kai
    0.40
     हमसे
    0.40
     কালি
    0.39
     lan
    0.39
     directing
    0.39
     sann
    0.39
     jud
    0.39
     tally
    0.38
    POSITIVE LOGITS
    CHA
    0.50
     ordinances
    0.46
    晧
    0.41
    깃
    0.39
     CHEMISTRY
    0.38
    ORDIN
    0.37
     obligations
    0.36
     Ordinance
    0.36
     SCALE
    0.36
    爾
    0.36
    Act Density 0.000%

    No Known Activations