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

    Neuronpedia

    INDEX
    Explanations

    inflation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Burgess
    -0.08
     GU
    -0.08
     calculus
    -0.07
     covering
    -0.07
    ec
    -0.07
     sequ
    -0.07
     George
    -0.07
     sequencing
    -0.07
     Conse
    -0.07
     edges
    -0.07
    POSITIVE LOGITS
     inflated
    0.07
    959
    0.06
     inflation
    0.06
    -il
    0.06
     上涨
    0.06
    plaint
    0.06
     향
    0.06
     inflatable
    0.06
    Already
    0.06
     drift
    0.06
    Act Density 0.005%

    No Known Activations