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

    Neuronpedia

    INDEX
    Explanations

    an encouraging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ​
    0.47
    _
    0.46
     ‎
    0.44
     ​
    0.43
    ́
    0.42
     COVID
    0.40
    ‑
    0.40
    ̈
    0.39
     |
    0.39
     ‏
    0.39
    POSITIVE LOGITS
    ᧐
    0.42
     pertaining
    0.42
     maken
    0.41
     þei
    0.41
     Ј
    0.41
    ԝ
    0.39
     insures
    0.39
     တော့
    0.38
     SLOT
    0.38
    abbanti
    0.38
    Act Density 0.000%

    No Known Activations