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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     immigrants
    -0.07
     red
    -0.07
    _sn
    -0.07
     immigrant
    -0.06
    macen
    -0.06
    ’yi
    -0.06
     наход
    -0.06
    чного
    -0.06
    -funded
    -0.06
     Land
    -0.06
    POSITIVE LOGITS
    言わ
    0.07
    ::::::::::::::::::::::::::::::::
    0.06
    403
    0.06
     protocols
    0.06
    าร
    0.06
    /Grid
    0.06
    <Texture
    0.06
    <small
    0.06
     Cologne
    0.06
     desserts
    0.06
    Act Density 0.003%

    No Known Activations