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

    Neuronpedia

    INDEX
    Explanations

    instructions and usage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zug
    -0.07
    anford
    -0.07
    .trip
    -0.06
     Bedford
    -0.06
    ính
    -0.06
    学会
    -0.06
    Financial
    -0.06
    dictions
    -0.06
     افز
    -0.06
    -Cs
    -0.06
    POSITIVE LOGITS
     lettre
    0.07
    	instance
    0.07
    leme
    0.06
     متحده
    0.06
     ")"
    0.06
    
    0.06
     quam
    0.06
     अम
    0.06
    _node
    0.06
    .'.$
    0.06
    Act Density 0.170%

    No Known Activations