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

    Neuronpedia

    INDEX
    Explanations

    circumstances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tut
    -0.07
     define
    -0.06
     wom
    -0.06
    입
    -0.06
     vå
    -0.06
    _lot
    -0.06
    Õ
    -0.06
     funktion
    -0.06
    ují
    -0.06
    _bool
    -0.06
    POSITIVE LOGITS
     circumstances
    0.27
    stances
    0.10
    ヶ月
    0.06
    ाहर
    0.06
     Woods
    0.06
     πρώ
    0.06
     Wayne
    0.06
     ingest
    0.06
     แพ
    0.06
    ']))
    0.06
    Act Density 0.002%

    No Known Activations