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

    Neuronpedia

    INDEX
    Explanations

    unusual words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    跟我
    -0.08
     podrá
    -0.07
     handing
    -0.07
    _finder
    -0.07
    -job
    -0.07
    (Convert
    -0.07
    機會
    -0.07
    ListBox
    -0.07
     thuế
    -0.06
     provides
    -0.06
    POSITIVE LOGITS
    _word
    0.07
     Privacy
    0.07
    ลงทะ
    0.07
    атур
    0.07
    reative
    0.06
     Dataset
    0.06
    ɜ
    0.06
    subj
    0.06
    옿
    0.06
     Liu
    0.06
    Act Density 0.004%

    No Known Activations