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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     massively
    -0.07
    anitize
    -0.07
    pletely
    -0.07
    .O
    -0.07
    single
    -0.06
     hp
    -0.06
     million
    -0.06
     accident
    -0.06
     comedian
    -0.06
     completely
    -0.06
    POSITIVE LOGITS
     yasak
    0.06
     만들어
    0.06
    서비스
    0.06
    .ex
    0.06
    emade
    0.06
    (posts
    0.06
    *angstrom
    0.05
    ість
    0.05
     coh
    0.05
    alse
    0.05
    Act Density 0.171%

    No Known Activations