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

    Neuronpedia

    INDEX
    Explanations

    COVID followed by nineteen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     malattie
    0.40
     melanoma
    0.38
     реда
    0.36
     microorganisms
    0.36
     lymphomas
    0.35
    ariously
    0.35
    利き
    0.35
    dise
    0.35
     glioma
    0.35
    aquin
    0.35
    POSITIVE LOGITS
    -
    0.51
    १९
    0.50
    ১৯
    0.49
     १९
    0.48
     ১৯
    0.47
     nineteen
    0.45
     ۱۹
    0.45
    ۱۹
    0.44
     toes
    0.42
     XIX
    0.40
    Act Density 0.001%

    No Known Activations