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

    Neuronpedia

    INDEX
    Explanations

    Comma

    np_max-act · gemini-2.0-flash

    The neuron is selectively activated by numerical tokens containing a decimal point (i.e. floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _ELEMENT
    -0.07
    backend
    -0.07
     Presentation
    -0.07
    XXXXXXXX
    -0.07
    |required
    -0.06
    環
    -0.06
     Anth
    -0.06
     Fot
    -0.06
     soap
    -0.06
    环
    -0.06
    POSITIVE LOGITS
     puedes
    0.07
     kinetic
    0.07
    ूचन
    0.07
    aine
    0.06
    CHEMY
    0.06
     jenis
    0.06
     날
    0.06
    環境
    0.06
     quiero
    0.06
     briefly
    0.06
    Act Density 0.001%

    No Known Activations