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

    Neuronpedia

    INDEX
    Explanations

    not or to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Database
    -0.08
    velop
    -0.07
     negotiated
    -0.07
    Read
    -0.07
     Times
    -0.07
     Nursery
    -0.07
     spin
    -0.06
     Lucy
    -0.06
     dropped
    -0.06
     Iterate
    -0.06
    POSITIVE LOGITS
     каш
    0.06
    อฟ
    0.06
     célib
    0.06
    \DependencyInjection
    0.06
     peux
    0.05
     tecr
    0.05
    emoc
    0.05
    getC
    0.05
    .small
    0.05
    .media
    0.05
    Act Density 0.011%

    No Known Activations