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

    Neuronpedia

    INDEX
    Explanations

    politics, influence, financing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Geschwindigkeit
    0.53
     gliding
    0.53
     ایپلی
    0.50
     snelheid
    0.50
     vollständig
    0.49
     vollständ
    0.48
     AppMethodBeat
    0.48
     énon
    0.47
     langsam
    0.47
     nécess
    0.46
    POSITIVE LOGITS
     lobbying
    0.65
    influence
    0.65
     финанси
    0.64
    financing
    0.63
    funding
    0.59
    financed
    0.59
    sponsored
    0.58
     रिश्वत
    0.57
    を通じて
    0.57
     lobbyists
    0.57
    Act Density 0.055%

    No Known Activations