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

    Neuronpedia

    INDEX
    Explanations

    words like C++, Python, XML

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reflective
    0.24
     reflectance
    0.24
     Mo
    0.23
    boden
    0.23
     reflectors
    0.23
    ological
    0.22
     Apollo
    0.22
     occult
    0.22
     osl
    0.22
     CV
    0.21
    POSITIVE LOGITS
    Jl
    0.27
    MPS
    0.24
    Pokemon
    0.23
    Capacity
    0.23
    ඩි
    0.23
    GTA
    0.23
    Eyes
    0.23
     Vince
    0.22
     अफ
    0.22
    Js
    0.22
    Act Density 0.000%

    No Known Activations