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

    Neuronpedia

    INDEX
    Explanations

    sponge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    les
    1.41
    ות
    1.41
    OT
    1.30
    3
    1.30
    AKER
    1.27
    Ale
    1.26
    IG
    1.24
    Part
    1.23
    েন্দু
    1.22
    Temp
    1.21
    POSITIVE LOGITS
    ている
    1.48
    ला
    1.31
    ています
    1.27
    㓡
    1.23
    های
    1.22
    萏
    1.20
    اعة
    1.18
    <0x9B>
    1.13
    opengl
    1.13
     revoc
    1.13
    Act Density 0.001%

    No Known Activations