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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    卖
    -0.07
    timeline
    -0.07
     till
    -0.07
     JSON
    -0.07
     gist
    -0.07
     Lonely
    -0.06
     list
    -0.06
    list
    -0.06
    ,lat
    -0.06
    287
    -0.06
    POSITIVE LOGITS
    4
    0.18
     Fourth
    0.10
     Four
    0.10
     four
    0.09
    54
    0.09
    ۴
    0.09
     Carolyn
    0.08
    -four
    0.08
    ४
    0.08
    Four
    0.08
    Act Density 0.410%

    No Known Activations