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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ентами
    -0.07
    Mic
    -0.06
    stm
    -0.06
    expr
    -0.06
     Bi
    -0.06
    CTION
    -0.06
    LOGIN
    -0.06
     ihnen
    -0.06
    -cart
    -0.06
    igi
    -0.06
    POSITIVE LOGITS
     BCH
    0.07
    achelor
    0.06
     Hoover
    0.06
     Tang
    0.06
     تولید
    0.06
     Eleanor
    0.06
     Indones
    0.06
     Plenty
    0.06
     여
    0.06
     DataView
    0.06
    Act Density 0.005%

    No Known Activations