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

    Neuronpedia

    INDEX
    Explanations

    oil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    楽しめる
    -0.07
    ấm
    -0.07
    后备
    -0.06
     região
    -0.06
     paź
    -0.06
    ṟ
    -0.06
    abric
    -0.06
     kısm
    -0.06
     гар
    -0.06
     vỏ
    -0.06
    POSITIVE LOGITS
    只是为了
    0.07
     Official
    0.07
                         ↵
    0.07
     mentioning
    0.07
    Transient
    0.07
    `.↵
    0.07
     lf
    0.07
    اخبار
    0.07
     /*↵
    0.07
     debugging
    0.07
    Act Density 0.007%

    No Known Activations