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

    Neuronpedia

    INDEX
    Explanations

    relate to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Scandal
    0.75
     sahabat
    0.71
     Club
    0.70
     Murder
    0.69
     Socialism
    0.68
    gmail
    0.67
     Destroyer
    0.65
     President
    0.65
    Murder
    0.64
     Empresas
    0.64
    POSITIVE LOGITS
     quantification
    0.61
     temperature
    0.60
     macroscopic
    0.60
     inhomogeneities
    0.60
     biasing
    0.60
     measurements
    0.58
     sutures
    0.57
     perturbations
    0.57
     geometries
    0.57
     microstructure
    0.56
    Act Density 0.000%

    No Known Activations