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

    Neuronpedia

    INDEX
    Explanations

    pause

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inions
    -0.07
     epic
    -0.06
    esehen
    -0.06
    显
    -0.06
    ario
    -0.06
     varargin
    -0.06
    Roman
    -0.06
    ального
    -0.06
    кра
    -0.06
    Sales
    -0.06
    POSITIVE LOGITS
     Nest
    0.07
    ˆ
    0.07
     Missouri
    0.07
     mentors
    0.07
    �다
    0.07
    _^(
    0.06
    _FIELD
    0.06
    igner
    0.06
    /↵↵↵↵
    0.06
    /interface
    0.06
    Act Density 0.005%

    No Known Activations