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

    Neuronpedia

    INDEX
    Explanations

    canals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TouchableOpacity
    -0.07
     Hollande
    -0.07
    oids
    -0.06
    _Type
    -0.06
    依
    -0.06
     lire
    -0.06
    .getLogin
    -0.06
    epend
    -0.06
     Kaepernick
    -0.06
    Domin
    -0.06
    POSITIVE LOGITS
     Canal
    0.13
     canal
    0.13
     castle
    0.08
    Λ
    0.07
    奈
    0.07
    al
    0.07
    海
    0.06
    quan
    0.06
    .qt
    0.06
    ải
    0.06
    Act Density 0.003%

    No Known Activations