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

    Neuronpedia

    INDEX
    Explanations

    technical terms and conditions related to specific functions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    atomic, uniform, setting, whatever

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     estekak
    -0.69
     OMITBAD
    -0.52
    bitField
    -0.45
    Cyfarwyddwr
    -0.44
    __':
    -0.42
    RegistryLite
    -0.41
    istoitu
    -0.40
    aarrggbb
    -0.39
     Autorizaciones
    -0.39
    Engineers
    -0.39
    POSITIVE LOGITS
    qrstuvwxyz
    0.50
     soft
    0.43
     SOFT
    0.43
    writeFieldEnd
    0.40
     Rap
    0.40
    copg
    0.39
    liziert
    0.38
     Cloud
    0.37
     CLOUD
    0.37
     cloud
    0.36
    Act Density 0.282%

    No Known Activations