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

    Neuronpedia

    INDEX
    Explanations

    handling affiliations and strengths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     struggles
    0.42
    س
    0.40
    heal
    0.39
     سرطان
    0.39
     inequ
    0.39
     রোগীর
    0.39
    க்க
    0.38
    explos
    0.38
     VERS
    0.38
     inequalities
    0.37
    POSITIVE LOGITS
     forage
    0.44
     prise
    0.40
    Dealer
    0.40
    Enterprise
    0.39
     Büro
    0.39
    othèque
    0.39
    ItemGroup
    0.38
     Order
    0.38
    Speech
    0.38
     적
    0.38
    Act Density 0.000%

    No Known Activations