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

    Neuronpedia

    INDEX
    Explanations

    morals and lessons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    minute
    -0.06
     оттен
    -0.06
     dirs
    -0.06
    iphertext
    -0.06
    .swap
    -0.06
     cre
    -0.06
    ,j
    -0.06
    .FontStyle
    -0.06
    .dir
    -0.06
     rectangles
    -0.06
    POSITIVE LOGITS
     lesb
    0.07
     reak
    0.06
    .modified
    0.06
     horns
    0.06
     Ton
    0.06
    .isAdmin
    0.06
    ?“
    0.06
    !“
    0.06
     Volk
    0.06
     sociology
    0.06
    Act Density 0.062%

    No Known Activations