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

    Neuronpedia

    INDEX
    Explanations

    households

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fading
    -0.07
    proper
    -0.07
     Proper
    -0.07
    Python
    -0.07
    ——
    -0.06
    tember
    -0.06
     تقویت
    -0.06
    orphic
    -0.06
    909
    -0.06
    _ORIENTATION
    -0.06
    POSITIVE LOGITS
     /\.
    0.07
                            ↵
    0.07
     venture
    0.06
     relieve
    0.06
                    ↵
    0.06
     legalize
    0.06
    	elseif
    0.06
    (material
    0.06
     opt
    0.06
    deadline
    0.06
    Act Density 0.000%

    No Known Activations