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

    Neuronpedia

    INDEX
    Explanations

    node_modules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     schimb
    0.42
     funnel
    0.41
     head
    0.40
     cabeza
    0.40
    頭
    0.40
    👨
    0.40
     막
    0.39
    改變
    0.38
     ड्र
    0.38
     scarcity
    0.38
    POSITIVE LOGITS
     modules
    0.42
    modules
    0.41
    zości
    0.38
    debris
    0.38
    erten
    0.37
    avorites
    0.37
     سپورټ
    0.37
     webpages
    0.37
    ériences
    0.37
    ASSOC
    0.37
    Act Density 0.000%

    No Known Activations