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

    Neuronpedia

    INDEX
    Explanations

    political future implications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     manually
    0.66
     workstation
    0.57
     file
    0.54
     File
    0.53
     flexible
    0.51
     комби
    0.51
     batch
    0.51
     sample
    0.50
     initial
    0.50
     elaborate
    0.50
    POSITIVE LOGITS
    政治
    1.32
     полити
    1.28
     políticos
    1.25
     राजनीतिक
    1.23
     political
    1.22
     político
    1.19
    political
    1.17
     політи
    1.16
     politiques
    1.13
     politics
    1.13
    Act Density 1.340%

    No Known Activations