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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of Slavic language or regional identifiers (e.g., Czech, Slovak, Polish).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Gun
    -0.07
    'am
    -0.06
     laz
    -0.06
    Hard
    -0.06
    SV
    -0.06
     lept
    -0.06
    _mobile
    -0.06
    	l
    -0.06
     tão
    -0.06
     ruby
    -0.06
    POSITIVE LOGITS
    vers
    0.07
    ै।
    0.07
    값
    0.07
     hardened
    0.07
     reserved
    0.07
     binnen
    0.06
    .ColumnStyle
    0.06
     Thorn
    0.06
     estates
    0.06
    erea
    0.06
    Act Density 0.051%

    No Known Activations