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

    Neuronpedia

    INDEX
    Explanations

    head

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enefit
    -0.07
     gays
    -0.07
    White
    -0.07
    ंभ
    -0.06
    Brown
    -0.06
     lul
    -0.06
     nation
    -0.06
     abril
    -0.06
     Czech
    -0.06
     LEVEL
    -0.06
    POSITIVE LOGITS
    objectManager
    0.07
     تسم
    0.07
    		↵	↵
    0.07
     [=[
    0.06
     저
    0.06
     slic
    0.06
    ぞ
    0.06
     karış
    0.06
    .xrLabel
    0.06
     OMG
    0.06
    Act Density 0.008%

    No Known Activations