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

    Neuronpedia

    INDEX
    Explanations

    estimate context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ning
    -0.10
    ocal
    -0.10
    /email
    -0.10
    ness
    -0.09
     McCl
    -0.09
    avir
    -0.09
    cre
    -0.09
    terr
    -0.09
     Ñģобой
    -0.08
    igger
    -0.08
    POSITIVE LOGITS
    -ce
    0.12
    ably
    0.11
    oppel
    0.11
    ache
    0.11
    hetic
    0.10
     sơ
    0.10
    ionage
    0.10
     Unidos
    0.10
    /app
    0.10
    ambre
    0.09
    Act Density 0.023%

    No Known Activations