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

    Neuronpedia

    INDEX
    Explanations

    ory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uplift
    -0.07
    阅读
    -0.07
    孙
    -0.06
    versation
    -0.06
     Documentary
    -0.06
    電影
    -0.06
    ="../
    -0.06
    男
    -0.06
     west
    -0.06
    .WriteHeader
    -0.06
    POSITIVE LOGITS
     temperament
    0.15
    &amp
    0.12
     TPM
    0.10
     Arbor
    0.09
     أكثر
    0.08
     маз
    0.07
     \<^
    0.07
    .HashMap
    0.07
    ERVER
    0.07
    allocator
    0.06
    Act Density 0.002%

    No Known Activations