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

    Neuronpedia

    INDEX
    Explanations

    route paths and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EMAIL
    0.47
    getPage
    0.43
     Blogs
    0.43
     EMAIL
    0.42
    andar
    0.42
    okra
    0.41
     Email
    0.41
    websocket
    0.41
     nacionales
    0.40
     nazionali
    0.40
    POSITIVE LOGITS
     interpolation
    0.43
     retry
    0.41
     renormalization
    0.41
     thermodynam
    0.39
     renormalized
    0.38
     finitely
    0.38
     actuation
    0.37
     weatherproof
    0.37
     Frobenius
    0.36
     out
    0.36
    Act Density 0.001%

    No Known Activations