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

    Neuronpedia

    INDEX
    Explanations

    Required

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nordic
    -0.08
    -C
    -0.07
    They
    -0.07
     C
    -0.07
     exc
    -0.07
     exclusively
    -0.07
    🍫
    -0.07
    _from
    -0.06
    芊
    -0.06
    duced
    -0.06
    POSITIVE LOGITS
     EINVAL
    0.07
     seis
    0.07
     iov
    0.07
    >)↵
    0.07
    팻
    0.07
    -fields
    0.07
     ואם
    0.06
    ForResult
    0.06
    ᄀ
    0.06
     affid
    0.06
    Act Density 0.002%

    No Known Activations