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

    Neuronpedia

    INDEX
    Explanations

    code related to error handling

    oai_token-act-pair · gemini-2.0-flash

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ijnt
    -0.59
    riedenheit
    -0.59
    arynx
    -0.55
    istad
    -0.54
    elashes
    -0.54
    metheus
    -0.53
     disappointing
    -0.52
    textTheme
    -0.52
     tiro
    -0.51
     cetera
    -0.51
    POSITIVE LOGITS
    OGND
    0.55
    0.54
     giapp
    0.53
    Bakgrunnsstoff
    0.52
    exitRule
    0.50
    SpringBootTest
    0.49
    Cyfarwyddwr
    0.48
    AndEndTag
    0.48
    Personendaten
    0.47
     AppModule
    0.47
    Act Density 1.700%

    No Known Activations