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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron activates primarily on floating-point numeric values (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     facing
    -0.06
     unwilling
    -0.06
     Kid
    -0.06
    bdb
    -0.06
     başında
    -0.06
     iki
    -0.06
     Raid
    -0.06
    /pay
    -0.06
     pupil
    -0.06
    icing
    -0.06
    POSITIVE LOGITS
     adrenal
    0.08
     můžete
    0.07
     избав
    0.07
     benefits
    0.06
    _Component
    0.06
     مقاو
    0.06
    带
    0.06
     thưởng
    0.06
    (Optional
    0.06
     RDF
    0.06
    Act Density 0.023%

    No Known Activations