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

    Neuronpedia

    INDEX
    Explanations

    people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Levels
    -0.08
    違い
    -0.07
     detail
    -0.06
    zego
    -0.06
     booze
    -0.06
    کاری
    -0.06
    due
    -0.06
    ssp
    -0.06
     ranges
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     SignUp
    0.06
     Sys
    0.06
    حاد
    0.06
     hosp
    0.06
    018
    0.06
     memberId
    0.06
    яют
    0.06
    ологичес
    0.06
    .Forms
    0.05
     @{$
    0.05
    Act Density 0.135%

    No Known Activations