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

    Neuronpedia

    INDEX
    Explanations

    varies from person to person

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ByDefault
    0.39
     Agencies
    0.37
    salaryfrom
    0.37
    ಂತಿ
    0.36
    浙
    0.36
     গান্ধ
    0.36
    $/.
    0.35
    '){$
    0.35
    ष्णु
    0.35
    FromThe
    0.35
    POSITIVE LOGITS
     በኋላ
    0.46
    autre
    0.43
     standpoint
    0.43
     seguinte
    0.42
     onwards
    0.41
     onward
    0.41
     depending
    0.39
     siguiente
    0.38
     appearances
    0.37
     vantage
    0.37
    Act Density 0.011%

    No Known Activations