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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pride
    -0.07
     safest
    -0.07
    (choice
    -0.06
     Instit
    -0.06
     jury
    -0.06
     uneasy
    -0.06
    .ALIGN
    -0.06
     forsk
    -0.06
     граж
    -0.06
    ####
    -0.06
    POSITIVE LOGITS
     외부
    0.06
     viol
    0.06
     đồ
    0.06
    ümü
    0.06
    (list
    0.06
    clientId
    0.06
     attendant
    0.06
    ButtonTitles
    0.06
     glucose
    0.06
     complement
    0.06
    Act Density 0.000%

    No Known Activations