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

    Neuronpedia

    INDEX
    Explanations

    human

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    の方
    -0.07
     Télé
    -0.07
     thao
    -0.07
    _permissions
    -0.07
     cinema
    -0.06
     leicht
    -0.06
     Mặt
    -0.06
     iar
    -0.06
    (top
    -0.06
    /open
    -0.06
    POSITIVE LOGITS
     продовж
    0.06
    �
    0.06
     इ
    0.06
    .setProperty
    0.06
    .nodeName
    0.06
    ACEMENT
    0.06
    .Inventory
    0.06
    적
    0.06
    .unsqueeze
    0.06
    witter
    0.06
    Act Density 0.021%

    No Known Activations