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

    Neuronpedia

    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blooms
    -0.08
     spiral
    -0.07
    ucher
    -0.07
     boca
    -0.07
    *>(
    -0.07
    icable
    -0.07
    778
    -0.06
     Glo
    -0.06
    orden
    -0.06
     Flood
    -0.06
    POSITIVE LOGITS
    SupportFragmentManager
    0.06
    .addMouseListener
    0.06
     싶
    0.06
     bullshit
    0.06
    .front
    0.06
    -community
    0.06
    Ό
    0.06
     έ
    0.06
    Portrait
    0.06
    duğu
    0.06
    Act Density 0.043%

    No Known Activations