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

    Neuronpedia

    INDEX
    Explanations

    EU parliament transcripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paddle
    -0.06
     blir
    -0.06
     wines
    -0.06
     -----------
    -0.06
     measured
    -0.06
     remodel
    -0.06
     NOP
    -0.06
     нег
    -0.06
     пож
    -0.06
     Dry
    -0.06
    POSITIVE LOGITS
    {_
    0.07
    _previous
    0.07
     wom
    0.07
    遠
    0.07
    ConnectionFactory
    0.07
     чуж
    0.07
     klub
    0.06
    _REASON
    0.06
    ("<?
    0.06
    .none
    0.06
    Act Density 0.015%

    No Known Activations