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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chicken
    -0.08
    🥓
    -0.07
    Ϭ
    -0.07
    locker
    -0.07
     watchdog
    -0.07
     katılı
    -0.06
     торр
    -0.06
    partials
    -0.06
    >>(
    -0.06
     sneakers
    -0.06
    POSITIVE LOGITS
    失踪
    0.07
    ################################################################################
    0.07
    Exposed
    0.07
    toInt
    0.06
     Rh
    0.06
     SL
    0.06
    Nh
    0.06
    Opts
    0.06
    SH
    0.06
    人格
    0.06
    Act Density 0.252%

    No Known Activations