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

    Neuronpedia

    INDEX
    Explanations

    until general elections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     поддержки
    0.50
     Cortez
    0.50
     dukungan
    0.48
     telas
    0.48
     Buffalo
    0.47
     bargaining
    0.46
     bureaucratic
    0.46
     rhythms
    0.45
     collaborations
    0.45
     Fundación
    0.45
    POSITIVE LOGITS
    Av
    0.51
    Anal
    0.48
    им
    0.47
    Ad
    0.47
    clust
    0.46
    TWO
    0.45
    lesen
    0.45
    Two
    0.45
    ům
    0.45
    Eu
    0.44
    Act Density 0.001%

    No Known Activations