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

    Neuronpedia

    INDEX
    Explanations

    classic question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     posible
    0.54
     catedral
    0.50
     indoct
    0.47
     makin
    0.46
    अधिका
    0.46
     cambiando
    0.46
     diseñar
    0.46
     maus
    0.46
     pavatt
    0.44
     continuando
    0.44
    POSITIVE LOGITS
     t
    0.38
    વેશ
    0.37
     pulverized
    0.36
    qrt
    0.36
     (<
    0.36
    டுகின்றன
    0.35
    倒入
    0.34
     elections
    0.34
     divert
    0.34
    HY
    0.34
    Act Density 0.006%

    No Known Activations