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

    Neuronpedia

    INDEX
    Explanations

    version numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proven
    0.75
     trừ
    0.73
     sound
    0.71
     traditions
    0.70
     territories
    0.69
    ച്ച
    0.68
     power
    0.68
     omissions
    0.68
     France
    0.66
    صحاب
    0.66
    POSITIVE LOGITS
     versione
    0.94
    ১
    0.90
    VERSION
    0.89
    Version
    0.88
    0
    0.86
    otesi
    0.85
    apiVersion
    0.84
     VERSION
    0.83
    1
    0.83
     одну
    0.82
    Act Density 0.004%

    No Known Activations