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

    Neuronpedia

    INDEX
    Explanations

    negative emotions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.52
    TAKT
    -0.50
    mappedBy
    -0.49
    ICATED
    -0.49
     fieldNum
    -0.49
    rouvez
    -0.48
    empêcher
    -0.46
    ParallelGroup
    -0.45
    цима
    -0.45
     prêtres
    -0.45
    POSITIVE LOGITS
     of
    0.76
    OnInit
    0.61
     deepen
    0.58
    setVerticalGroup
    0.57
     isComment
    0.53
     deepening
    0.53
    posób
    0.53
    ExtendWith
    0.52
     OnInit
    0.50
     SID
    0.50
    Act Density 0.005%

    No Known Activations