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

    Neuronpedia

    INDEX
    Explanations

    Background information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dusk
    -0.08
     Transfer
    -0.07
    rdquo
    -0.07
    .nil
    -0.07
     Community
    -0.07
    els
    -0.07
     infusion
    -0.07
     pentru
    -0.07
     mida
    -0.07
    orgetown
    -0.07
    POSITIVE LOGITS
     notoriously
    0.11
     العديد
    0.11
    许
    0.10
     uitgerust
    0.10
    拥有
    0.10
     많은
    0.10
     көптеген
    0.10
    많
    0.09
    很多
    0.09
     다양한
    0.09
    Act Density 0.208%

    No Known Activations