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

    Neuronpedia

    INDEX
    Explanations

    Code/Formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     خوب
    -0.06
     Bedford
    -0.06
     dific
    -0.06
    免
    -0.06
     looph
    -0.06
     disdain
    -0.06
    .ttf
    -0.06
    จะ
    -0.06
     también
    -0.06
    .combine
    -0.06
    POSITIVE LOGITS
    ется
    0.08
    papers
    0.08
     Jefferson
    0.07
    мель
    0.06
    焦
    0.06
     southern
    0.06
    -ion
    0.06
     WebSocket
    0.06
     등의
    0.06
     +**************
    0.06
    Act Density 0.000%

    No Known Activations