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

    Neuronpedia

    INDEX
    Explanations

    house

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    公认
    -0.07
    alten
    -0.07
     amb
    -0.07
    とりあえ
    -0.07
    ề
    -0.07
     Belgium
    -0.07
     Light
    -0.07
    apphire
    -0.07
     thép
    -0.07
    商业地产
    -0.07
    POSITIVE LOGITS
     rins
    0.07
    .Attributes
    0.07
    Mutable
    0.07
     crim
    0.07
    _histogram
    0.07
     incapable
    0.07
    儿子
    0.07
     jim
    0.06
     Rep
    0.06
     cage
    0.06
    Act Density 0.053%

    No Known Activations