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

    Neuronpedia

    INDEX
    Explanations

    specific objects and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     조건
    0.75
    getConfig
    0.73
     Dataset
    0.73
     Environments
    0.73
    З
    0.71
    А
    0.71
     Systems
    0.70
    Experiment
    0.70
     Config
    0.70
    实践
    0.69
    POSITIVE LOGITS
     entire
    0.92
     affected
    0.84
     gesamte
    0.81
     underlying
    0.76
     actual
    0.73
     resulting
    0.73
     shiny
    0.72
     stricken
    0.71
     offending
    0.71
     underside
    0.71
    Act Density 1.225%

    No Known Activations