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

    Neuronpedia

    INDEX
    Explanations

    on the / in mature / on first / using the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CDMA
    0.49
     fax
    0.44
    сии
    0.42
     preferably
    0.41
     желательно
    0.41
    OTHER
    0.41
    fZ
    0.40
    ALL
    0.40
     quaerat
    0.40
     causing
    0.40
    POSITIVE LOGITS
    日常
    0.52
     TikTok
    0.51
     metaverse
    0.51
     playground
    0.50
     everyday
    0.47
     Metaverse
    0.46
    esperienza
    0.45
     festivals
    0.45
     Instagram
    0.45
     playgrounds
    0.45
    Act Density 0.000%

    No Known Activations