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

    Neuronpedia

    INDEX
    Explanations

    blogging, logging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discover
    -0.07
     tricks
    -0.07
     perceive
    -0.07
     misunderstanding
    -0.07
     weapons
    -0.06
     Educational
    -0.06
    Enable
    -0.06
     developing
    -0.06
    >(&
    -0.06
     переход
    -0.06
    POSITIVE LOGITS
     blogger
    0.09
     Blogger
    0.09
     blogging
    0.08
     bloggers
    0.07
    echn
    0.07
    _DH
    0.06
     mdb
    0.06
    ğ
    0.06
    oggle
    0.06
    äh
    0.06
    Act Density 0.006%

    No Known Activations