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

    Neuronpedia

    INDEX
    Explanations

    opening applications and starting processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mortality
    0.40
     Maladies
    0.39
     Sensitivity
    0.39
     Lov
    0.37
     uncontrollable
    0.37
     Conflict
    0.36
     Sahara
    0.36
     Charcoal
    0.36
     Microbiology
    0.36
     Sexuality
    0.36
    POSITIVE LOGITS
    erçe
    0.46
    我们将
    0.41
     będ
    0.40
    我們要
    0.39
    我们要
    0.38
     yapacağız
    0.38
    Pod
    0.38
     végét
    0.37
     allons
    0.36
    ensee
    0.36
    Act Density 0.001%

    No Known Activations