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

    Neuronpedia

    INDEX
    Explanations

    user input context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ing
    0.81
    uous
    0.80
    સ્ક
    0.74
    ectomy
    0.74
    ative
    0.74
     учу
    0.72
    phere
    0.72
    son
    0.71
    ्स
    0.71
    mercial
    0.71
    POSITIVE LOGITS
     submitted
    0.84
     Moira
    0.81
    LoggedIn
    0.81
    Login
    0.80
     يريد
    0.78
    Chrome
    0.78
     login
    0.78
    login
    0.77
     Specified
    0.76
     Visible
    0.75
    Act Density 0.132%

    No Known Activations