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

    Neuronpedia

    INDEX
    Explanations

    names of people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    calar
    -0.07
     Hughes
    -0.07
    ABB
    -0.06
    annon
    -0.06
    /engine
    -0.06
     Nielsen
    -0.06
     podařilo
    -0.06
    .Account
    -0.06
     Manuel
    -0.06
    _ops
    -0.06
    POSITIVE LOGITS
    stein
    0.08
     Rosenstein
    0.08
     Sherman
    0.07
     mdl
    0.07
     Levine
    0.07
     Unt
    0.07
     judgments
    0.06
     ấy
    0.06
    trib
    0.06
     Rubin
    0.06
    Act Density 0.023%

    No Known Activations