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

    Neuronpedia

    INDEX
    Explanations

    react libraries and components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Alien
    0.41
    แอ
    0.41
    nta
    0.41
    InvalidArgument
    0.40
     anthropological
    0.40
    Naive
    0.39
    zza
    0.39
     ఓ
    0.38
    oak
    0.37
    üller
    0.37
    POSITIVE LOGITS
    intersection
    0.51
     intersection
    0.43
     Intersection
    0.41
    PLAYER
    0.40
     sabb
    0.40
    terminal
    0.39
     amal
    0.39
     face
    0.38
    effort
    0.38
    ([{
    0.38
    Act Density 0.000%

    No Known Activations