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

    Neuronpedia

    INDEX
    Explanations

    Google App Engine and Datastore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gloria
    0.41
    atoires
    0.39
     o
    0.37
     Cardiac
    0.37
     brand
    0.36
     Junior
    0.36
     hydro
    0.36
     Details
    0.36
     cardiac
    0.36
     раст
    0.36
    POSITIVE LOGITS
    gql
    0.51
    Blob
    0.46
     худо
    0.42
    Blending
    0.41
    信念
    0.40
    spě
    0.40
     PROPERTY
    0.39
     Blob
    0.39
    Ancestor
    0.39
    weaving
    0.39
    Act Density 0.005%

    No Known Activations