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

    Neuronpedia

    INDEX
    Explanations

    templateUrl

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Moira
    0.47
     innov
    0.40
     விட
    0.39
    不妨
    0.39
    bounded
    0.38
    linewidth
    0.38
    விட
    0.37
    örm
    0.36
    KHTML
    0.36
    MRS
    0.36
    POSITIVE LOGITS
    lysninger
    0.38
     afară
    0.38
     backups
    0.37
     الح
    0.36
     যুক্তরাষ্ট্রের
    0.35
     американ
    0.35
     যুক্তরাষ্ট্রে
    0.35
    ;.
    0.35
     lamina
    0.35
     additionally
    0.34
    Act Density 0.000%

    No Known Activations