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

    Neuronpedia

    INDEX
    Explanations

    target assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.50
    K
    0.49
    비
    0.48
    Cl
    0.47
     народов
    0.45
     наме
    0.45
    B
    0.45
    IAL
    0.45
    Intent
    0.44
    鱔
    0.44
    POSITIVE LOGITS
     todavía
    0.56
    angé
    0.50
    erkraut
    0.50
     clasific
    0.50
     नियुक्ति
    0.48
     nejen
    0.47
     লেখকের
    0.46
     शीर्षक
    0.46
    viendo
    0.46
    geving
    0.45
    Act Density 0.000%

    No Known Activations