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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Detail
    -0.08
    TabPage
    -0.07
     technique
    -0.07
    Ti
    -0.07
     Após
    -0.07
     lw
    -0.07
     Vib
    -0.07
     detectives
    -0.07
     Courage
    -0.07
     Titanium
    -0.07
    POSITIVE LOGITS
     הו
    0.07
    .activities
    0.07
    Classes
    0.07
     العسكري
    0.07
     brut
    0.06
     repent
    0.06
    直到
    0.06
     الث
    0.06
     ulong
    0.06
     ''
↵
    0.06
    Act Density 0.080%

    No Known Activations