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

    Neuronpedia

    INDEX
    Explanations

    code, distance, vaccines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Handler
    0.81
    HISTORY
    0.79
     Maryland
    0.76
    Origins
    0.76
    和谐
    0.75
     Freunden
    0.74
     História
    0.73
     mendukung
    0.73
    توى
    0.72
    Support
    0.72
    POSITIVE LOGITS
    ertype
    0.84
    parte
    0.80
    planet
    0.77
    proces
    0.74
     реак
    0.73
     respond
    0.72
    bus
    0.72
     type
    0.71
     universit
    0.70
    type
    0.67
    Act Density 0.003%

    No Known Activations