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

    Neuronpedia

    INDEX
    Explanations

    sections of Java code declaring static final integer constants.

    oai_token-act-pair · gemini-2.0-flash

    static

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     GenerationType
    -1.21
    Jeografia
    -1.00
     protoimpl
    -0.99
     propOrder
    -0.96
     Efq
    -0.95
    MENAFN
    -0.94
    TagMode
    -0.94
    complexContent
    -0.93
    principalTable
    -0.92
    =$?
    -0.92
    POSITIVE LOGITS
     finish
    0.46
     her
    0.45
     fini
    0.45
     послед
    0.45
     finally
    0.44
    末
    0.43
     “
    0.42
     no
    0.42
     finishes
    0.41
     s
    0.41
    Act Density 0.053%

    No Known Activations