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

    Neuronpedia

    INDEX
    Explanations

    properties

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    阊
    -0.07
     Chall
    -0.07
    auled
    -0.07
     BBQ
    -0.07
     Bills
    -0.07
    资深
    -0.07
     knack
    -0.06
    Nom
    -0.06
     booths
    -0.06
     Sullivan
    -0.06
    POSITIVE LOGITS
    𝗘
    0.07
     uncont
    0.07
    .extensions
    0.07
    ece
    0.07
     because
    0.07
    .edges
    0.07
    ^(
    0.06
    尽量
    0.06
     ينبغي
    0.06
    CAST
    0.06
    Act Density 0.004%

    No Known Activations