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

    Neuronpedia

    INDEX
    Explanations

    Brokkr, consequences, click, yet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Nar
    0.48
    Food
    0.47
    warm
    0.45
     Additionally
    0.45
    曏
    0.45
    Warm
    0.45
     定
    0.44
    expects
    0.44
    ↵
    0.44
    PHYS
    0.44
    POSITIVE LOGITS
     yapıyor
    0.54
     inscrib
    0.51
     entretien
    0.50
    ณา
    0.47
     cytosolic
    0.46
    ი
    0.46
     terren
    0.46
     difficile
    0.45
     interesante
    0.45
     manipul
    0.45
    Act Density 0.000%

    No Known Activations