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

    Neuronpedia

    INDEX
    Explanations

    Crisis Text Line

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Variable
    0.70
     स्किप
    0.66
    Antae
    0.64
    ⓪
    0.63
     Drying
    0.62
     देवगन
    0.62
     Vari
    0.61
     Adaptive
    0.61
     Nano
    0.60
    প্লে
    0.60
    POSITIVE LOGITS
    साइड
    0.62
     জো
    0.56
     பெண்களுக்கு
    0.54
    𝐈
    0.52
    carbon
    0.51
     সড়কের
    0.50
    igor
    0.50
     carbon
    0.50
     switch
    0.50
    car
    0.50
    Act Density 0.277%

    No Known Activations