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

    Neuronpedia

    INDEX
    Explanations

    warranty

    np_max-act · gemini-2.0-flash

    The neuron activates on the word “WARRANTY” in software license disclaimer headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    usalem
    -0.06
    Shop
    -0.06
     cutoff
    -0.06
     unofficial
    -0.06
     antibody
    -0.06
    　↵
    -0.06
     Allocation
    -0.06
     hat
    -0.06
     vicious
    -0.06
     sug
    -0.06
    POSITIVE LOGITS
     WARRANTY
    0.08
    (klass
    0.07
    =set
    0.06
     TER
    0.06
     Cort
    0.06
    ΗΝ
    0.06
    (java
    0.06
     komple
    0.06
    OURSE
    0.06
    !');↵
    0.06
    Act Density 0.001%

    No Known Activations