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

    Neuronpedia

    INDEX
    Explanations

    imperative

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    それぞれ
    -0.08
    氨基酸
    -0.08
    ontology
    -0.07
    找
    -0.07
    zin
    -0.07
     !***
    -0.07
    consult
    -0.07
    illes
    -0.07
    .blogspot
    -0.07
    撤
    -0.07
    POSITIVE LOGITS
     sexy
    0.07
    新房
    0.06
     pthread
    0.06
    craper
    0.06
    Ϋ
    0.06
    ihu
    0.06
     fifo
    0.06
    _FACTOR
    0.06
    .worker
    0.06
    _STMT
    0.06
    Act Density 0.001%

    No Known Activations