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

    Neuronpedia

    INDEX
    Explanations

    further or another

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ത്തിലാണ്
    0.76
     اولا
    0.70
    inaan
    0.70
    である
    0.69
     ControllerBase
    0.69
    𝕕
    0.68
    事前に
    0.68
    യിലാണ്
    0.67
     మొద
    0.67
    itattu
    0.67
    POSITIVE LOGITS
     further
    4.55
     weitere
    3.96
    further
    3.95
    Further
    3.93
     Further
    3.84
     weiteren
    3.82
    进一步
    3.65
     additional
    3.60
     weiterer
    3.60
     ulteriori
    3.47
    Act Density 0.845%

    No Known Activations