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

    Neuronpedia

    INDEX
    Explanations

    business contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    䓨
    -0.08
    应
    -0.07
    来形容
    -0.07
     exercises
    -0.07
    мя
    -0.07
    ᡞ
    -0.07
     eğer
    -0.07
    ’av
    -0.07
     amacıyla
    -0.07
    接收
    -0.07
    POSITIVE LOGITS
     cru
    0.08
    Gran
    0.07
     Src
    0.07
    (groups
    0.07
    蟥
    0.07
     robber
    0.07
    バス
    0.07
    roid
    0.06
    맙
    0.06
    Transition
    0.06
    Act Density 0.108%

    No Known Activations