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

    Neuronpedia

    INDEX
    Explanations

    Initials

    np_max-act · gemini-2.0-flash

    This neuron detects individual capital-letter initials (letters followed by a period) in names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    SAVE
    -0.08
     Dodd
    -0.06
     да
    -0.06
     Haw
    -0.06
    entieth
    -0.06
    ол
    -0.06
    Inspector
    -0.06
     Ni
    -0.06
     xương
    -0.06
     Shelter
    -0.06
    POSITIVE LOGITS
     URLs
    0.07
     teknoloj
    0.07
     reveal
    0.07
     vous
    0.06
    _ctl
    0.06
     RN
    0.06
    PRS
    0.06
    ș
    0.06
     RTBU
    0.06
    Estimated
    0.06
    Act Density 0.101%

    No Known Activations