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

    Neuronpedia

    INDEX
    Explanations

    Period token

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Context
    -0.08
    ction
    -0.08
    /socket
    -0.08
    -between
    -0.07
     الأه
    -0.07
    _detach
    -0.07
     overcrow
    -0.07
    bers
    -0.07
    뻐
    -0.07
    invalidate
    -0.07
    POSITIVE LOGITS
     cours
    0.08
    Manual
    0.07
     Hawaiian
    0.07
     notebook
    0.07
     أقل
    0.07
     IMPORTANT
    0.07
     projectName
    0.07
     pipes
    0.06
     einz
    0.06
    维生素
    0.06
    Act Density 0.001%

    No Known Activations