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

    Neuronpedia

    INDEX
    Explanations

    usage options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    0.49
    पल
    0.48
     अंगों
    0.45
    dot
    0.43
     ocupa
    0.42
     manzanas
    0.42
    Dots
    0.41
     pantalones
    0.41
     whack
    0.40
    neos
    0.40
    POSITIVE LOGITS
    atsioon
    0.44
     Wasn
    0.40
     Umfang
    0.38
    íř
    0.37
     жүкт
    0.36
     duplicating
    0.36
    arran
    0.35
    ικό
    0.35
    的服务
    0.35
    ovíd
    0.35
    Act Density 0.000%

    No Known Activations