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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kis
    -0.08
     Freem
    -0.07
     prem
    -0.07
     contracting
    -0.07
     preached
    -0.06
     "[
    -0.06
     converse
    -0.06
     incidence
    -0.06
     disciples
    -0.06
     Molecular
    -0.06
    POSITIVE LOGITS
    ChartData
    0.07
    rgba
    0.07
    _stack
    0.06
     мяг
    0.06
    роз
    0.06
    offs
    0.06
    _chunks
    0.06
     gdy
    0.06
     �
    0.06
    _objs
    0.06
    Act Density 0.016%

    No Known Activations