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

    Neuronpedia

    INDEX
    Explanations

    get lost

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     naive
    0.52
     ie
    0.48
     manglid
    0.48
     ans
    0.47
     &=&
    0.47
     semantics
    0.46
     sii
    0.46
     adiabatic
    0.46
     conservatives
    0.45
     bores
    0.45
    POSITIVE LOGITS
    l
    0.55
    ISER
    0.43
    sion
    0.43
    碰撞
    0.43
    ಾ
    0.43
    ्हा
    0.43
    五
    0.43
    一下
    0.42
    Loading
    0.42
     Terc
    0.42
    Act Density 0.004%

    No Known Activations