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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surpassed
    -0.07
    .LinearLayout
    -0.06
     weir
    -0.06
     devastated
    -0.06
     getUsers
    -0.06
     tiế
    -0.06
     offended
    -0.06
    ذه
    -0.06
    ################################################################################↵
    -0.06
     Kitty
    -0.06
    POSITIVE LOGITS
     acceptable
    0.07
     proposal
    0.06
    /server
    0.06
    п
    0.06
     sme
    0.06
    _LEG
    0.06
     Thick
    0.06
    =set
    0.06
    设计
    0.06
    indsight
    0.06
    Act Density 0.005%

    No Known Activations