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

    Neuronpedia

    INDEX
    Explanations

    Sensory Comfort, Input, Grounding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ແລະ
    0.51
     ടി
    0.47
     detto
    0.46
     și
    0.45
     gubit
    0.44
     rode
    0.44
     thiab
    0.43
     dimensioni
    0.43
     പ്രേ
    0.42
     regol
    0.42
    POSITIVE LOGITS
    r
    0.56
    u
    0.54
    e
    0.51
     chrys
    0.50
    implement
    0.48
    covariant
    0.47
    cym
    0.46
    setting
    0.45
    important
    0.44
    erian
    0.44
    Act Density 0.001%

    No Known Activations