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

    Neuronpedia

    INDEX
    Explanations

    even *

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     homely
    0.40
    contrad
    0.39
    꽉
    0.39
     عجیب
    0.39
     Literally
    0.39
     Phenomenology
    0.38
     vyu
    0.38
    Filling
    0.38
     pleated
    0.38
     करीत
    0.38
    POSITIVE LOGITS
     having
    0.61
     mere
    0.57
     contemplate
    0.55
    Mere
    0.52
     иметь
    0.50
    Having
    0.50
     Mere
    0.50
     merely
    0.49
    mere
    0.48
     possessing
    0.48
    Act Density 0.011%

    No Known Activations