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

    Neuronpedia

    INDEX
    Explanations

    notes and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disbursements
    0.48
     ಕ್ಷೇತ್ರದ
    0.46
    特定の
    0.46
    sPath
    0.46
     gruppi
    0.46
     electrification
    0.45
    务
    0.45
    itati
    0.45
    ्यूटर
    0.45
    rivez
    0.45
    POSITIVE LOGITS
     Hopefully
    0.59
     Delicious
    0.57
     Kids
    0.56
     Thanks
    0.54
     This
    0.52
     Thank
    0.51
     Beautiful
    0.50
     Tasty
    0.49
     Cute
    0.49
     Microbial
    0.49
    Act Density 0.002%

    No Known Activations