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

    Neuronpedia

    INDEX
    Explanations

    advisory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ınca
    -0.07
     Fuck
    -0.07
     blend
    -0.07
     slik
    -0.07
    ht
    -0.07
    ↵	↵
    -0.07
     Finnish
    -0.06
    .Spec
    -0.06
    лада
    -0.06
     Sex
    -0.06
    POSITIVE LOGITS
     Advisory
    0.13
     advisory
    0.11
     advisor
    0.11
     advisors
    0.11
     Advisor
    0.09
     adviser
    0.09
     Advisors
    0.08
     advisers
    0.08
     cdr
    0.07
     counselor
    0.07
    Act Density 0.004%

    No Known Activations