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

    Neuronpedia

    INDEX
    Explanations

    numbers in years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     January
    0.56
     October
    0.56
     December
    0.53
     June
    0.52
     Winter
    0.52
     जानेवारी
    0.51
     November
    0.49
     winter
    0.49
     February
    0.47
     зимой
    0.47
    POSITIVE LOGITS
    птовалю
    0.42
    Sector
    0.41
    Zobacz
    0.40
    hiqdev
    0.40
    АН
    0.39
    Sala
    0.39
    Severity
    0.39
     assertTrue
    0.39
     සා
    0.39
    Proof
    0.39
    Act Density 0.011%

    No Known Activations