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

    Neuronpedia

    INDEX
    Explanations

    ת

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    afd
    -0.07
    .sharedInstance
    -0.07
     Merr
    -0.07
     staveb
    -0.06
     giảng
    -0.06
     guild
    -0.06
    _responses
    -0.06
     pueblo
    -0.06
    Marvel
    -0.06
     spaces
    -0.06
    POSITIVE LOGITS
    ת
    0.08
     прос
    0.07
     ابت
    0.07
     contacted
    0.07
    osal
    0.07
    ceeded
    0.07
    、お
    0.06
     footnote
    0.06
    αλύτε
    0.06
     Copyright
    0.06
    Act Density 0.002%

    No Known Activations