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

    Neuronpedia

    INDEX
    Explanations

    beginnings, specific places, names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    㻐
    0.48
    fehlung
    0.44
    ్యాచ్
    0.44
    Reasoner
    0.43
    荩
    0.43
     നടപ
    0.42
    晔
    0.42
    सरकारी
    0.41
    ן
    0.41
    錒
    0.41
    POSITIVE LOGITS
    begin
    0.47
    ,
    0.46
     confined
    0.43
    -
    0.42
     connected
    0.42
     semi
    0.41
    able
    0.41
     start
    0.41
     customizable
    0.40
     llega
    0.39
    Act Density 0.000%

    No Known Activations