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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     renseignements
    -0.46
     négociations
    -0.46
     émissions
    -0.46
    twimg
    -0.45
     économies
    -0.44
     vaisseaux
    -0.44
     bienfaits
    -0.43
     matériaux
    -0.42
     modalités
    -0.42
     autorités
    -0.41
    POSITIVE LOGITS
     summits
    0.98
     fronts
    0.90
     necks
    0.89
     aprons
    0.88
     mouths
    0.87
     ends
    0.87
     throats
    0.86
     craters
    0.82
     hoods
    0.82
     fountains
    0.82
    Act Density 0.023%

    No Known Activations