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

    Neuronpedia

    INDEX
    Explanations

    Development/Production environments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ndan
    0.42
    нуу
    0.36
    ⩾
    0.36
    idden
    0.34
    leden
    0.34
    λης
    0.34
    死的
    0.34
     구분
    0.34
     citas
    0.34
    懷
    0.34
    POSITIVE LOGITS
    And
    0.49
     And
    0.46
     aul
    0.42
    Vol
    0.41
    yl
    0.41
    Running
    0.41
     Running
    0.40
    Runner
    0.40
     മാത്രമേ
    0.40
     Incoming
    0.40
    Act Density 0.001%

    No Known Activations