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

    Neuronpedia

    INDEX
    Explanations

    route path element

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dielectric
    0.47
    ều
    0.41
     turpentine
    0.40
     hydrochloric
    0.39
     hydraz
    0.39
    Jung
    0.39
     histidine
    0.38
    োলজি
    0.38
     envej
    0.38
     yam
    0.37
    POSITIVE LOGITS
     element
    0.69
    element
    0.63
     ROUTES
    0.56
     Route
    0.53
     ELEMENT
    0.53
     Routes
    0.52
     exact
    0.52
     Element
    0.52
     élément
    0.51
    要素
    0.50
    Act Density 0.002%

    No Known Activations