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

    Neuronpedia

    INDEX
    Explanations

    phrases related to humanitarian efforts and community support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Positive feedback for someone's efforts

    np_acts-logits-general · gemini-2.0-flash

    work and efforts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kháu
    -0.62
     NgModule
    -0.54
    RegressionTest
    -0.52
     חיצוניים
    -0.49
     jumping
    -0.49
    Viited
    -0.48
     שוליים
    -0.47
    DIRS
    -0.47
    databind
    -0.47
    toHave
    -0.46
    POSITIVE LOGITS
     work
    1.39
     efforts
    1.23
    efforts
    1.07
    work
    1.05
     Efforts
    1.00
     trabalho
    0.98
    工作
    0.96
     lavoro
    0.95
     trabalhos
    0.94
     работы
    0.94
    Act Density 0.121%

    No Known Activations