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

    Neuronpedia

    INDEX
    Explanations

    baby

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CASE
    -0.53
    pric
    -0.51
    ValueGeneration
    -0.49
    之
    -0.47
    etsu
    -0.47
     ouverte
    -0.46
     propo
    -0.46
    etary
    -0.45
    ner
    -0.45
    ăn
    -0.45
    POSITIVE LOGITS
    Personendaten
    0.60
    ftagPool
    0.58
     referenties
    0.58
     TestBed
    0.57
     виправивши
    0.56
    ⓧ
    0.55
    Hrsg
    0.55
     nahilalakip
    0.54
    webElementGuid
    0.54
     Roskov
    0.54
    Act Density 0.001%

    No Known Activations