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

    Neuronpedia

    INDEX
    Explanations

    words relating to opinions or statements from a viewpoint

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     okuyayım
    -0.71
    Brainz
    -0.66
     HasFactory
    -0.61
    وأضاف
    -0.60
     eventdata
    -0.60
     jScrollPane
    -0.60
     experimenter
    -0.57
    Transkript
    -0.57
    NegativeButton
    -0.57
     يتيمه
    -0.57
    POSITIVE LOGITS
     stance
    0.97
     position
    0.78
     stances
    0.70
    Positions
    0.69
     positions
    0.69
     attitude
    0.68
     Positions
    0.66
     standpoint
    0.66
    PRNewswire
    0.65
    trato
    0.62
    Act Density 0.015%

    No Known Activations