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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mount
    -0.08
     workshop
    -0.07
    ::↵
    -0.07
    izons
    -0.07
     developing
    -0.07
    放射
    -0.07
     PDT
    -0.07
     Cor
    -0.07
    _da
    -0.07
     Ston
    -0.07
    POSITIVE LOGITS
     {
    0.10
    {
    0.10
    {{{
    0.08
    btc
    0.07
    “All
    0.07
    nemonic
    0.07
     Newest
    0.07
    ->{
    0.06
    ,{
    0.06
    rases
    0.06
    Act Density 0.114%

    No Known Activations