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

    Neuronpedia

    INDEX
    Explanations

    what makes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apakah
    0.44
     সহায়তা
    0.42
    稞
    0.40
    🔁
    0.39
    𝑳
    0.38
    🔙
    0.38
    ereum
    0.38
     vasomotor
    0.38
     yalnızca
    0.38
    🤰
    0.38
    POSITIVE LOGITS
     Latest
    0.40
     Pacific
    0.39
     Riverside
    0.39
    Launch
    0.39
     Legislative
    0.38
     rats
    0.38
     Finnish
    0.38
    輕
    0.38
     轻
    0.38
     Norwegian
    0.37
    Act Density 0.003%

    No Known Activations