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

    Neuronpedia

    INDEX
    Explanations

    weather and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    спублі
    0.41
    Notably
    0.41
     Virus
    0.40
    onds
    0.39
    зил
    0.38
     വിമ
    0.38
    Lib
    0.38
    norod
    0.37
    aren
    0.37
     Beno
    0.37
    POSITIVE LOGITS
    ;}
    0.43
     ज
    0.39
     DSM
    0.39
     edible
    0.37
     chiffres
    0.36
     DSC
    0.36
     caveats
    0.36
    от
    0.36
     DSL
    0.36
    告
    0.35
    Act Density 0.004%

    No Known Activations