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

    Neuronpedia

    INDEX
    Explanations

    common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     laminated
    -0.11
    apache
    -0.09
    conomic
    -0.09
     apache
    -0.09
    liess
    -0.08
    /mysql
    -0.08
    .rmi
    -0.08
     milho
    -0.08
     lector
    -0.08
     nobles
    -0.08
    POSITIVE LOGITS
     rooftop
    0.10
    <Rigidbody
    0.09
     rehab
    0.09
     MTV
    0.09
     unstoppable
    0.09
     eslint
    0.08
     fades
    0.08
     faded
    0.08
     restless
    0.08
     �
    0.08
    Act Density 0.033%

    No Known Activations