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

    Neuronpedia

    INDEX
    Explanations

    the word "by" or "to", often next to numbers, formulas, code, or legal language

    oai_token-act-pair · gemini-2.0-flash

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.66
    HostException
    -0.62
     Roskov
    -0.62
    السكان
    -0.60
     temprana
    -0.59
    AndEndTag
    -0.59
    BufferException
    -0.57
    djangoproject
    -0.57
    assade
    -0.56
     Italijani
    -0.56
    POSITIVE LOGITS
    сион
    0.56
    rungsseite
    0.54
    
    0.53
    斯特
    0.48
    ביוגרפיה
    0.47
    和
    0.47
    ณ์
    0.46
     Sac
    0.46
     saites
    0.46
     estre
    0.45
    Act Density 5.032%

    No Known Activations