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

    Neuronpedia

    INDEX
    Explanations

    specific tasks and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    旳
    0.37
    0.34
    Ა
    0.34
    𝓑
    0.33
    ashions
    0.32
     संजय
    0.31
    funktion
    0.31
    मतौर
    0.31
     तकनीकी
    0.31
    embangunan
    0.31
    POSITIVE LOGITS
    哪怕
    0.33
     teeming
    0.30
     platelets
    0.29
    গ্র
    0.29
    令牌
    0.29
    全体の
    0.29
    .”
    0.28
     overall
    0.28
     dimers
    0.28
     Dishes
    0.28
    Act Density 0.132%

    No Known Activations