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

    Neuronpedia

    INDEX
    Explanations

    Summarization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ark
    -0.08
     peter
    -0.07
     schließen
    -0.07
     matplotlib
    -0.07
     ఇద్ద
    -0.07
     DFS
    -0.07
     vtk
    -0.07
     mathem
    -0.07
    thermal
    -0.07
    NET
    -0.07
    POSITIVE LOGITS
     everything
    0.08
     تحت
    0.08
     obedient
    0.08
     breakdown
    0.08
     राश
    0.08
    yeah
    0.07
    ್ರಮ
    0.07
    everything
    0.07
     seguida
    0.07
     raccol
    0.07
    Act Density 0.004%

    No Known Activations