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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "regular."

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

    standard or typical version

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SpaceX
    -0.51
     Nanotechnology
    -0.46
    AISSEE
    -0.45
    HashCode
    -0.44
    HostException
    -0.44
     cladding
    -0.44
    MockBean
    -0.44
     piercings
    -0.43
    hlmann
    -0.43
    Hozzáférés
    -0.43
    POSITIVE LOGITS
     regular
    2.05
    regular
    1.96
    Regular
    1.91
     Regular
    1.87
     REGULAR
    1.84
    REGULAR
    1.69
     regulares
    1.51
     regulars
    1.43
     regularly
    1.36
     régulière
    1.36
    Act Density 0.008%

    No Known Activations