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

    Neuronpedia

    INDEX
    Explanations

    Tony

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     清
    -0.07
     		↵
    -0.07
    (crate
    -0.06
     करत
    -0.06
     К
    -0.06
     bufsize
    -0.06
     creep
    -0.06
     breakup
    -0.06
     fleets
    -0.06
    ificial
    -0.06
    POSITIVE LOGITS
     Tony
    0.18
    Tony
    0.17
     Anthony
    0.13
    Anthony
    0.12
     Jonathan
    0.10
     Antony
    0.10
    Jonathan
    0.09
     Tory
    0.08
     Toni
    0.08
    ony
    0.08
    Act Density 0.005%

    No Known Activations