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

    Neuronpedia

    INDEX
    Explanations

    Beginning of clauses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ABA
    -0.07
     Christie
    -0.07
    aba
    -0.07
     VAN
    -0.06
    _limits
    -0.06
     objection
    -0.06
    สมาช
    -0.06
     Baxter
    -0.06
     Austin
    -0.06
     Lawson
    -0.06
    POSITIVE LOGITS
     Corn
    0.07
    (sort
    0.07
    默默地
    0.07
     departamento
    0.07
    _unc
    0.07
    雍
    0.06
     art
    0.06
     '',
    0.06
     servers
    0.06
    蓂
    0.06
    Act Density 0.150%

    No Known Activations