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

    Neuronpedia

    INDEX
    Explanations

    feel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Taylor
    -0.06
    求购
    -0.06
     Chevrolet
    -0.06
     favorable
    -0.06
    蔵
    -0.06
    іки
    -0.06
     territory
    -0.06
    сторія
    -0.06
     prosecutions
    -0.06
    toolbox
    -0.06
    POSITIVE LOGITS
     feels
    0.08
     cảm
    0.08
     felt
    0.08
     lv
    0.07
     Allow
    0.07
     роботу
    0.07
     ph
    0.07
     raced
    0.06
    /id
    0.06
     TOO
    0.06
    Act Density 0.033%

    No Known Activations