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

    Neuronpedia

    INDEX
    Explanations

    the word "on" or "and" along with a verb

    oai_token-act-pair · gemini-2.0-flash

    on/at

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MENAFN
    -0.69
    CloseOperation
    -0.67
    SharedDtor
    -0.66
    Datuak
    -0.66
    RefNanny
    -0.63
    Ծանոթ
    -0.62
    tagHelperRunner
    -0.59
    XmlAccessType
    -0.59
    CompleteListener
    -0.57
     tartalomajánló
    -0.56
    POSITIVE LOGITS
     making
    0.92
     creating
    0.89
     giving
    0.85
     restoring
    0.81
     providing
    0.80
     solving
    0.78
     implementing
    0.78
     having
    0.77
     adding
    0.76
     finding
    0.75
    Act Density 2.146%

    No Known Activations