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

    Neuronpedia

    INDEX
    Explanations

    essential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     returnPacket
    0.55
     conduz
    0.54
     ৰ
    0.52
    水の
    0.52
     przen
    0.51
    𝕘
    0.51
    くなる
    0.50
    𝚞
    0.50
    ナソニック
    0.49
    ຮູ້
    0.49
    POSITIVE LOGITS
    ick
    0.53
    ings
    0.52
    ai
    0.52
    ung
    0.51
    y
    0.48
    ab
    0.47
     Bulgarian
    0.47
     parseFloat
    0.46
    ed
    0.45
    am
    0.45
    Act Density 0.001%

    No Known Activations