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

    Neuronpedia

    INDEX
    Explanations

    tls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     guarding
    -0.07
    SetActive
    -0.07
    投融资
    -0.07
    将军
    -0.07
     rejected
    -0.07
     +#+
    -0.07
    -equiv
    -0.06
    出租车
    -0.06
    胀
    -0.06
    fab
    -0.06
    POSITIVE LOGITS
     erase
    0.07
     Aber
    0.07
    婍
    0.07
    ٲ
    0.07
    VERTISEMENT
    0.07
    节
    0.07
    nested
    0.07
    𝔞
    0.06
    ompiler
    0.06
    _compiler
    0.06
    Act Density 0.024%

    No Known Activations