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

    Neuronpedia

    INDEX
    Explanations

    would

    np_max-act · gemini-2.0-flash

    The neuron selectively responds to the token “to,” marking infinitive markers in text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .OnClickListener
    -0.07
    หม
    -0.07
    Pot
    -0.06
    аного
    -0.06
    
    -0.06
    ahi
    -0.06
    ISO
    -0.06
    application
    -0.06
    fork
    -0.06
    лерг
    -0.06
    POSITIVE LOGITS
     {$
    0.07
     Lim
    0.06
     stát
    0.06
    ">{
    0.06
    saldo
    0.06
     amend
    0.06
    includes
    0.06
    Backdrop
    0.06
     Primitive
    0.06
    ραση
    0.06
    Act Density 0.027%

    No Known Activations