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

    Neuronpedia

    INDEX
    Explanations

    phrases of the form "the more" or "the better"

    oai_token-act-pair · gemini-2.0-flash

    comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.70
     Execute
    -0.56
     ainfi
    -0.53
     disampaikan
    -0.52
     createState
    -0.52
     professionali
    -0.51
     fotografico
    -0.50
     noDo
    -0.50
     personali
    -0.50
    lapsingToolbar
    -0.49
    POSITIVE LOGITS
    numerusform
    0.66
    DockStyle
    0.61
     باخ
    0.55
    BrowserModule
    0.53
    rawDesc
    0.51
    клопе
    0.50
    GIH
    0.50
     BrowserModule
    0.49
    loem
    0.49
    UserScript
    0.48
    Act Density 0.833%

    No Known Activations