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

    Neuronpedia

    INDEX
    Explanations

    Future plans

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -percent
    -0.07
     recept
    -0.07
    分辨
    -0.07
    ensis
    -0.07
     Purdue
    -0.07
    hx
    -0.07
    一味
    -0.07
     Maharashtra
    -0.07
    verige
    -0.07
    icana
    -0.06
    POSITIVE LOGITS
    'L
    0.07
    <tag
    0.06
     l
    0.06
    🚧
    0.06
    _week
    0.06
    ⋘
    0.06
    थ
    0.06
    <L
    0.06
    clip
    0.06
    ...'
    0.06
    Act Density 0.068%

    No Known Activations