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

    Neuronpedia

    INDEX
    Explanations

    AI assistant, helpful partner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ☬
    0.38
    .".,
    0.35
     bū
    0.35
    ]]).
    0.35
    бу
    0.34
    ainty
    0.34
     पुनः
    0.33
    "-------
    0.33
     zare
    0.33
    BDT
    0.33
    POSITIVE LOGITS
     Ask
    0.53
     AI
    0.52
     Study
    0.48
     Stud
    0.47
     chatbot
    0.47
     docs
    0.44
    Ask
    0.44
    Study
    0.43
    AI
    0.42
    Stud
    0.42
    Act Density 0.000%

    No Known Activations