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

    Neuronpedia

    INDEX
    Explanations

    Descriptions with labeled details

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    п
    -0.07
     створ
    -0.06
    uran
    -0.06
     sensitive
    -0.06
     succes
    -0.06
    .but
    -0.06
    ADDRESS
    -0.06
     bother
    -0.06
    Me
    -0.06
     soared
    -0.06
    POSITIVE LOGITS
    swing
    0.07
     bác
    0.06
     eclectic
    0.06
    -core
    0.06
    ких
    0.06
     unseen
    0.06
    alers
    0.06
     ки
    0.06
     COMPANY
    0.06
     AuthService
    0.06
    Act Density 0.000%

    No Known Activations