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

    Neuronpedia

    INDEX
    Explanations

    advanced

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -buy
    -0.08
     Hou
    -0.07
    nothing
    -0.06
    faker
    -0.06
     yarn
    -0.06
    .Inject
    -0.06
     Bit
    -0.06
     Ping
    -0.06
     feelings
    -0.06
     Nutrition
    -0.06
    POSITIVE LOGITS
     advances
    0.11
     Advance
    0.11
     advance
    0.11
     advanced
    0.10
     Advances
    0.09
    advance
    0.09
     Advanced
    0.09
    Advance
    0.09
     aide
    0.08
     Adv
    0.08
    Act Density 0.020%

    No Known Activations