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

    Neuronpedia

    INDEX
    Explanations

    math calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Plays
    -0.07
    deadline
    -0.06
    .directory
    -0.06
    chants
    -0.06
     Boca
    -0.06
     Danny
    -0.06
     rabbit
    -0.06
     Cannes
    -0.06
    .Car
    -0.06
    inson
    -0.06
    POSITIVE LOGITS
     contentious
    0.07
    /environment
    0.07
    aclass
    0.07
    л
    0.06
     labeling
    0.06
     дов
    0.06
     popular
    0.06
     referenced
    0.06
     cải
    0.06
    _ack
    0.06
    Act Density 0.050%

    No Known Activations