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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron activates on HTML form input elements (the “<input>” tags and their attributes).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Exchange
    -0.06
    かし
    -0.06
     Mbps
    -0.06
    	cuda
    -0.06
     Ж
    -0.06
    (argc
    -0.06
    桂
    -0.06
    _iteration
    -0.05
     각각
    -0.05
    .putInt
    -0.05
    POSITIVE LOGITS
     VN
    0.08
    .Rel
    0.07
     pyt
    0.07
     fkk
    0.07
     tick
    0.07
    perty
    0.06
    owering
    0.06
    .""
    0.06
     推
    0.06
    atan
    0.06
    Act Density 0.303%

    No Known Activations