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

    Neuronpedia

    INDEX
    Explanations

    Definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iae
    -0.07
    概念
    -0.07
     sequences
    -0.07
     System
    -0.07
    ологіч
    -0.07
    Fish
    -0.07
    terror
    -0.06
    LEGAL
    -0.06
    _MEMORY
    -0.06
    maal
    -0.06
    POSITIVE LOGITS
    广
    0.06
    ussions
    0.06
    _E
    0.06
    0.06
     "@
    0.06
    ırken
    0.06
     {}).
    0.06
    	Q
    0.06
    @endsection
    0.06
    _.
    0.06
    Act Density 0.067%

    No Known Activations