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

    Neuronpedia

    INDEX
    Explanations

    writing reports

    np_max-act · gemini-2.0-flash

    The neuron activates on Cyrillic-script tokens, effectively detecting Russian-language text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     photographic
    -0.07
    ATIONAL
    -0.07
     masking
    -0.06
     روست
    -0.06
     blue
    -0.06
     trajectories
    -0.06
     Allen
    -0.06
     socks
    -0.06
     GPA
    -0.06
    ximity
    -0.06
    POSITIVE LOGITS
    ?',
    0.07
     HDMI
    0.06
     پزش
    0.06
    лия
    0.06
    '%
    0.06
    '")↵
    0.06
    /reset
    0.06
    .det
    0.06
    _ef
    0.06
     getS
    0.06
    Act Density 0.078%

    No Known Activations