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

    Neuronpedia

    INDEX
    Explanations

    packaged items, choice, or travel destination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Conductivity
    0.77
     vécu
    0.72
     exemplifies
    0.68
     такі
    0.68
     guérison
    0.68
    и
    0.68
    ە
    0.68
     Centuries
    0.67
    虍
    0.67
    egraphics
    0.67
    POSITIVE LOGITS
    av
    0.85
    son
    0.84
    bang
    0.82
    day
    0.79
    うちに
    0.79
    zi
    0.78
    bc
    0.77
    na
    0.77
    sol
    0.76
     '.
    0.76
    Act Density 0.001%

    No Known Activations