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

    Neuronpedia

    INDEX
    Explanations

    loss and grief

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Socrates
    0.49
    valids
    0.46
     ಇದರಿಂದ
    0.46
    ០
    0.46
    ÈRES
    0.46
    ⎮
    0.45
     เร
    0.45
    STRUCTIONS
    0.44
     করোনাভাই
    0.43
     RTR
    0.43
    POSITIVE LOGITS
    ension
    0.55
     water
    0.50
     nexus
    0.46
     winter
    0.46
     molecule
    0.45
    "
    0.45
     precinct
    0.45
     flower
    0.45
     heter
    0.45
     wetland
    0.44
    Act Density 0.001%

    No Known Activations