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

    Neuronpedia

    INDEX
    Explanations

    currently

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ǧ
    -0.08
    reveal
    -0.07
    自然灾害
    -0.07
     Zag
    -0.07
    .trailing
    -0.07
     dvd
    -0.07
     sudden
    -0.07
     Red
    -0.07
     survey
    -0.07
    经纪
    -0.07
    POSITIVE LOGITS
    _contacts
    0.07
    _http
    0.07
    hell
    0.07
    categoria
    0.07
    حيا
    0.07
     ngủ
    0.07
    镍
    0.06
    ками
    0.06
     Cove
    0.06
    iciente
    0.06
    Act Density 0.022%

    No Known Activations