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

    Neuronpedia

    INDEX
    Explanations

    operators and code symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fixing
    0.74
    mediated
    0.73
     fixation
    0.67
    ᑯ
    0.65
     ಸಮಯದಲ್ಲಿ
    0.63
    ント
    0.63
    ថា
    0.63
     dissolved
    0.63
     kiệm
    0.61
     పదార్థ
    0.60
    POSITIVE LOGITS
     ⭐
    0.84
     emotes
    0.84
     zio
    0.84
     SharePoint
    0.83
    𝐑
    0.82
     intellig
    0.81
     Pokémon
    0.81
    ********/
    0.81
     amicable
    0.81
     Admin
    0.80
    Act Density 0.271%

    No Known Activations