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

    Neuronpedia

    INDEX
    Explanations

    model, jo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	fields
    -0.07
    _dyn
    -0.07
    setWidth
    -0.07
     pur
    -0.06
     وف
    -0.06
    ,var
    -0.06
     Perry
    -0.06
     thirst
    -0.06
     Trek
    -0.06
     cooled
    -0.06
    POSITIVE LOGITS
    ALAR
    0.07
    ayed
    0.07
     sorumlu
    0.07
     Idle
    0.06
    ैसल
    0.06
    asley
    0.06
     consistency
    0.06
    _complex
    0.06
     honorary
    0.06
    ISMATCH
    0.06
    Act Density 0.101%

    No Known Activations