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

    Neuronpedia

    INDEX
    Explanations

    accented characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᱟ
    0.46
     turkeys
    0.46
    ọt
    0.44
    िंट
    0.44
    ोह
    0.41
    oyed
    0.41
    শোধ
    0.41
    િયલ
    0.41
    েকের
    0.41
    𝙱
    0.41
    POSITIVE LOGITS
    béco
    0.61
    ́
    0.57
    ร์
    0.52
    nd
    0.52
    ٰ
    0.50
    ̀
    0.50
    rm
    0.49
    rv
    0.48
    ng
    0.47
    sc
    0.47
    Act Density 0.048%

    No Known Activations