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

    Neuronpedia

    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     numbered
    -0.08
    ��
    -0.07
    ITLE
    -0.07
    ังกล
    -0.07
    veřej
    -0.06
    innitus
    -0.06
    ��
    -0.06
    駆
    -0.06
    .fp
    -0.06
    иплом
    -0.06
    POSITIVE LOGITS
    CNT
    0.07
    (handler
    0.06
     grate
    0.06
     filling
    0.06
    -temp
    0.06
     writers
    0.06
    pr
    0.06
    …↵
    0.06
     Penn
    0.06
    ner
    0.06
    Act Density 0.000%

    No Known Activations