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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     testCase
    -0.08
    �
    -0.08
     Sơn
    -0.07
     lacked
    -0.07
    (expected
    -0.07
    urm
    -0.07
     Wilde
    -0.07
     ";↵↵
    -0.07
    ≥
    -0.07
    𝖐
    -0.07
    POSITIVE LOGITS
     cancellation
    0.08
     póź
    0.08
    انخفاض
    0.07
     Ağust
    0.07
    当地时间
    0.07
    굵
    0.07
     alignment
    0.07
    Ἕ
    0.07
    abilities
    0.07
     confidentiality
    0.07
    Act Density 0.023%

    No Known Activations